What's New
A running summary of how Aelo has evolved. We ship frequently; this page highlights the customer-visible changes — new capabilities, meaningful improvements, and the occasional important fix. For a full role-by-role guide to everything the platform does today, see the User Guide.
Dates reflect when each change reached production. Internal-only work (infrastructure, tests, refactors) is omitted.
- «Transcript only» mode. For a project whose calls and chats you need as text: turn it on in the project’s settings, on the Analysis & Quality tab, on every plan including Pay as you go. A call is transcribed, categorized and indexed for search and the assistant, but not analyzed, and its minute counts as 0.25 of a minute (a 5:10 call uses 1.30 minutes); a chat costs a quarter of the chat price. The record is marked «Transcript without analysis» and offers Analyze when you need the full analysis after all: it charges a full minute (the full chat price) on top of the quarter already paid, and shows the price before it starts. Switching the mode off returns the project to its previous automatic analysis setting.
- The user guide shows the real interface. The articles about the product’s screens now carry screenshots in all four languages, and Getting started walks through sign-up, the setup wizard and the compliance screen as you will see them.
- Sorting the Records table orders the whole list. Click a column header and every matching record is sorted, not only the ones already loaded: «QA» ascending puts the lowest score of all first, and records without a value go last. Previous/next in a record follow the same order.
- Try Aelo before you sign up. The live demo lets you ask the assistant about a sample deal and see its state, scores and quotes with timestamps.
- One consent step in Uspacy. Connecting Aelo in Uspacy now takes two checkboxes, as in Bitrix24: the Terms of Service with the Uspacy Integration Terms and the Data Processing Agreement, accepted on behalf of your organization, and the Uspacy Integration Privacy Notice. The consent screen asks only for what is still missing.
- Answered Uspacy calls reach Aelo again. Uspacy reports an answered call with a status Aelo did not recognize, so answered calls from Uspacy were not taken in; Aelo now reads the status exactly as Uspacy sends it. Calls missed before this release are not recovered.
- An active Uspacy installation gets every function, whichever version of the processing instruction it accepted: importing the org structure and starting a record no longer ask you to accept the current instruction first.
- In Bitrix24, the organization’s owner is the administrator who installed the app. Only the person who installed Aelo and was a portal administrator at that moment can take ownership, and they accept the Terms and the DPA on behalf of the organization. An integrator who installs Aelo for a client gets the Admin role, and the client’s portal administrator becomes the owner by reinstalling Aelo and then opening it; anyone else who opens Aelo joins as a Rep.
- Smart-process items show the call time in the organization’s time zone, the same as the deal comment, and the CRM report writes the model’s tags (a competitor mention’s tone, a feedback’s severity and the like) in the report’s language.
- A closed section says so. Opening an address your access does not cover shows «No access to this section» instead of a silent redirect, and Call statistics, Missed calls and Objections say «Unavailable with your access» when your access lacks the capability.
- «My score» in a rep’s digest is the number on the Mine tab: a whole score, and its change in points; the ranking line names the same place as the tab’s «My position» card.
- An alert rule on a paused criterion reads «paused», and pausing a criterion of your own that enabled rules use asks first.
- Command palette: Enter opens the record you found, with no «No results» flash while the search is still answering; «reports» finds the Analytics reports.
- The intake log speaks your language for every reason it shows, and the Brazilian Portuguese interface, emails and CRM comments follow a full proofreading.
- Terms of Service 1.12, the Data Processing Agreement 1.65 and the Uspacy texts are in force from 16 November 2026. The Uspacy processing instruction is part of the DPA, and the DPA says who accepts it for an organization and how it changes.
- A new dashboard for everyone. The dashboard is now the same for every role and has six tabs: Summary, Conversations, Sales, Quality, Team and Voice of Customer, with one filter panel (period, comparison, projects, channel, demo data) that stays in the page address. A rep gets one tab, Mine, with their own results. What you see follows your role and access: an Analyst access sees aggregates only, a Group lead sees their departments. Sales and Voice of Customer are available on Pro and above and shown locked on lower plans. Charts by day and hour open as a table with the Table button, and the criteria report — every criterion, the built-in ones included — has its own place under Analytics → Criteria report. In Bitrix24 the tabs replace Overview. The new dashboard replaces the Owner, Supervisor and Rep dashboards and the Highlights and Criteria tabs; their numbers live on in the new tabs.
- Email digests for people with a narrow access. A person who holds an Analyst or Group lead access now receives the daily and weekly digest and the monthly Voice of Customer email built for that access, instead of no digest at all: only the area and the sections the access opens, with no records, quotes or audio, and rep names only with Rep scores and ranking. A Rep with a Group lead access gets the department letter instead of a personal one. The monthly Voice of Customer email is sent on Pro and above.
- Digests count quality the way the dashboard does. The quality change is now shown in points (“4 pts up”), not in percent, and the supervisor’s top rep and rep at risk follow the rules of the Team tab: only reps with at least 5 scored conversations in the period are rated, and a rep below 70 is never named top rep.
- Reports, CRM comments and emails in Brazilian Portuguese. An organization can now choose Portuguese (Brazil) as its language, and a Bitrix24 portal in Brazilian Portuguese gets it at installation. The analysis report in the CRM, the deal-state comment and the CRM task, digests, Voice of Customer, invitations, alerts and notifications then come in Portuguese, and Portuguese can be a project’s report language. Built-in criteria, templates, default scripts and the demo data are translated too. The app interface speaks Portuguese too: pick Português in the language switcher, and the Bitrix24 app on a Brazilian portal opens in Portuguese by itself; the Uspacy extension has a Portuguese version. The website and the docs are not translated yet and open in English.
- Import the org structure from Uspacy. Import from CRM now works for Uspacy as it does for Bitrix24: departments, their members, employees still waiting for an Aelo account and department heads come from the portal’s employee directory; dismissed employees and application bots are left out. For Uspacy the import reads the directory once the portal has accepted the current processing instruction, and only the organization owner runs it. For both CRMs, a re-import follows the head the portal names now, while a head assigned by hand still wins, and a directory that cannot be read in full stops the import instead of importing part of it.
- Organization time zone. A Brazilian team can pick America/São Paulo — Brasília (UTC-3). An organization that has not chosen a time zone now runs on Europe/Kyiv everywhere, as its settings already said: its daily and weekly email reports go out at 08:00 Kyiv time instead of 08:00 UTC, and the deal-state comment in the CRM shows the time next to the date.
- Reinstalling the app resumes calls on its own. Removing the Uspacy app switches the source off but no longer withdraws your organization’s authorization: installing the app again brings calls, reports and deal-state comments back with no new consent — unless the processing instruction the portal accepted is outdated: then an owner or administrator confirms the current one first. A pause or a withdrawal you made yourself stays in place. Uspacy does not always report a new installation to Aelo yet: then the app still asks to be reinstalled.
- A banner when calls from a CRM are not arriving — while the app is removed from the portal and no other CRM still brings calls, or while its processing is paused or not authorized. Everyone sees which CRM stopped and who can fix it; the owner or an administrator gets a button to Settings → Consent Management.
- The connection no longer expires after two weeks without calls. Aelo now renews it on a schedule, so a holiday or a seasonal pause no longer means reinstalling the app.
- The app says who takes the next step. On a portal linked to an existing Aelo organization, the app points to an owner or administrator under Settings → Consent Management instead of the installer, and the consent card no longer shows “active” while new calls do not arrive.
- A new sign-in email becomes your account address. Change your verified primary email in the sign-in profile, and Aelo moves your account — money notices, digests, the news subscription — to it the next time you open the app (Aelo checks at most once every five minutes).
- A paused project uses no minutes after the pause. A call or chat accepted before its project was paused or archived is now closed with the reason The project was paused or archived instead of being transcribed, analyzed and charged once its recording arrives. A manual start and a re-analysis are not affected.
- The criterion quote on an alert card shows its moment in the call: clicking the time opens the call there, when the moment is known, and “Quote unavailable” is now told apart from “No quote: event not found”.
- A criterion’s scope can include any project, not only the first 100, and an edit panel stays open with your unsaved changes when someone archives the criterion in another tab.
- Lists of people stay current. After an invitation, a role change, a deletion or a CRM import, the pickers and widgets show the change at once instead of after their cache expires.
- Clearer states. A chat that closed with no text says “The chat closed with no messages” in Settings → Service status instead of counting as a failure, and a report opened with a project outside your access says “No access” instead of “Could not load” with a retry that could not help.
- Accepting an invitation is one step. The invited person ticks the Terms and the Privacy Policy and presses Accept Invitation: the account is created and they land in the organization, with no separate sign-up. The invitation email greets them by the name the admin gave, or with no name, instead of the part of the address before the @.
- Built-in criteria update by themselves. When Aelo improves a built-in criterion, the organizations that use it get the change in hourly batches after the update, with no action on your side.
- An alert rule on a paused criterion no longer fires, whether the criterion is built-in or your own: the rule is marked as one that never fires, and a new rule on a paused criterion is refused.
- Two people editing one criterion no longer overwrite each other. Saving a form opened before someone else changed the criterion’s question, guidance, values or word list is refused with “Someone changed this criterion in the meantime”, and the form keeps what you typed.
- The onboarding checklist and tour work on the new dashboard, with tour steps about its tabs, the period and the filters.
- Voice of Customer reads “someone else decides” more precisely (Pro and above): such a no stays a decline unless the conversation moved on, and the monthly email says when there is no comparison with last month because the reading was updated.
- Signing up from a Bitrix24 portal no longer creates a second organization: someone who signs up after pressing “Open portal” is taken to linking the portal instead of the onboarding wizard.
- Business-intelligence tags read as words on the call screen and in the PDF report, in all four languages, instead of raw codes, and opening one category of a call’s analysis shows its cards expanded.
One name for the person in the conversation, an org structure built by hand, and intake you can see · 26.57
- One name for the person in the conversation: Rep, Asesor, Менеджер. The
person who holds the conversation is now called Rep in English,
Asesor in Spanish and Менеджер in Russian and Ukrainian — on screens,
in emails (digests, signal emails, the invitation), in the analysis report
written to the CRM and in this documentation — instead of “agent” and
“employee”. In Russian and Ukrainian the Supervisor role is now
Руководитель / Керівник in the role lists and the documentation (it
was «Супервизор» / «Супервізор» on screens). The two built-in criteria about
the rep’s language are renamed: Rep used profanity and Rep used a
forbidden word in English, El asesor usó groserías and El asesor usó
una palabra prohibida in Spanish. Only the names change: the questions of the
built-in criteria, which the model reads, keep their wording, and the scores
stay the same. Organizations that already use
built-in criteria get the new names during the day of this update. API fields
and role identifiers (such as
agent_id) do not change, and older entries of this page keep the words of their time. - Build the org structure by hand. An organization without a CRM import builds its department tree itself: on the Org structure tab of Settings → Team & Access the Owner adds, renames, moves and deletes departments and sets each department’s members; a department with sub-departments is deleted only after them. Department heads see their part of the tree exactly as with an imported one. All plans.
- The tree has one source. An imported tree changes only in the CRM and with a new import; the head is still assigned by hand. Importing over a hand-built tree asks for confirmation and replaces it whole — Group lead access to the removed departments is revoked; importing from another CRM replaces the tree too, where it used to leave both side by side. Manage manually turns an imported tree into a hand-built one, keeping departments, members, heads and accesses; people still waiting for an Aelo account leave it. A person who joined a department by invitation stays visible to their head instead of disappearing until the next import; a person who joined before this update reappears with the next import.
- The tree reads by level, and the access window warns about digests. On Org structure, department names of one level now stand on one line, with a guide for every ancestor level, and depth is no longer cut at five levels. The window that grants access to a person now says that, while the access is in force, the person gets no daily or weekly digest and no Voice of Customer digest (access grants are Pro and above).
- Everyone sees when recordings are not being received. Until the owner confirms the organization’s compliance, Aelo accepts no recordings, and a rep used to see nothing at all. Every member who cannot confirm it now sees a permanent banner on every screen, in the web app and inside the CRM, with the owner’s name when it is known, and where to confirm.
- Fact verification now stops only the CRM card fields. An analysis whose
only reason for holding is an unconfirmed fact no longer stops everything: the
card fields stay unwritten, but tasks are created from confirmed agreements,
call-back checks run and the deal state is built (the deal state is Pro and
above). An unconfirmed agreement gets no task and does not reach
the deal state. A safety signal, a role conflict, an ambiguous category, a
verification that could not be completed or failed personal-data minimisation
still stop everything. The CRM note, the report email and the record screen
name the fact in question; the webhook carries it as
verification.questioned_facts, and itsautomation_allowedstaysfalsebecause the card fields were withheld, even when tasks were created. Approving a manual review releases the card fields and the unconfirmed agreements. Only for conversations analysed after this update; an analysis stored earlier keeps holding tasks too. - A telephony call lost at intake shows in the intake log. A call whose recording never arrived within 3 days now leaves a row in Analysis Setup → Distribution → Log with the reason “Call not received — the recording never arrived”, instead of disappearing without a trace. It concerns telephony integrations that cannot fetch a recording by its id.
- A chat waiting for a start shows its conversation. A chat in Manual mode, or stopped for lack of funds, now shows its text on the record card before any analysis: the text arrives with the chat, so only the analysis waits. The start button stays in view on narrow panels, and the notice on such a chat no longer says “call”. Calls are unchanged: their audio is not downloaded until the analysis is started.
- The first consent asks “company or client?” On Bitrix24 the first person to accept the Terms and Privacy Policy becomes the organization’s Owner, so an integrator who opened a fresh install before the customer took ownership left the customer’s administrator a Rep. While the organization has no Owner, the consent screen now asks whether the person represents the company or is setting the app up for a client. “For a client” gives the Admin role and leaves ownership open for the company’s own representative; “this company” works as before. Once there is an Owner nobody is asked. The answer is self-declared.
- Fewer analyses held back over fields that are not written. A CRM field is checked only when this delivery will write it: a Smart Process destination, autofill off, a field outside the autofill list or a low-confidence value leaves it unchecked and unwritten, so it can no longer withhold automation. A free-text field such as the comment is checked fact by fact — each fact needs its own quote, and one refuted fact still removes the field. Only conversations analysed after this release.
- Satisfaction guarantee: choosing a size no longer counts as a doubt. The built-in criterion Explained the satisfaction guarantee now answers Not applicable when the customer is only choosing a size or fit, checking measurements or changing the size before shipping. It stays applicable when the customer says they may return the item, states a doubt outright, or the rep offers a return or exchange on their own in case it does not suit. Organizations that already use built-in criteria get the new wording during the day of this update.
- A closed deal reads “Closed”. In the deal queue and on the deal card, a deal closed in the CRM — and a lead converted into a deal — shows “Closed” instead of the chance to close, and its next action is not marked overdue. Pro and above.
- A short call is one thing everywhere. A Bitrix24 call under 15 seconds is
shown with the “short” mark in the deal card’s feed, the record card no longer
offers Analyze for it, and polling the public API for its analysis returns
reason: "short_call", so an integrator can tell it from any other record closed without an analysis. - Alert importance is shown truthfully. The badge and icon in the inbox
follow the importance of the rule that fired — an alert from a Low rule was
shown as High. A notification cut down for the holder of an access grant (Pro and
above) carries no importance in any channel, and the webhook’s
severityis the rule’s importance, no longer alwayshigh. - A rule on a criterion outside its project is refused. A criterion is evaluated only on the projects of its scope, so an alert rule of project A on a criterion limited to project B used to save and never fire. Saving it now fails with a message that names the criterion, and an existing rule like that is marked “doesn’t cover this rule’s project”. Two routing rules can no longer take the same manual priority.
- A message accepted before its project was paused no longer starts paid processing. A message can wait in the queue while its project is paused or archived or its channel is switched off; it now refuses with the same reason in the intake log instead of creating a record and starting processing.
- An interrupted intake no longer loses or duplicates a call. A retry after an interrupted attempt finishes the intake of the same record instead of being dropped as a duplicate or starting a second one.
- Audio saved during a deletion is deleted too. A recording saved at the moment its record or project was deleted is now removed as well — the deletion the Privacy Policy and the DPA already promise.
- Team, the Quality card and the data-source banner. After Approve in Access requests the new member appears in the team table without a reload, and revoking an invitation or syncing CRM users refreshes every member list. An access grant (Pro and above) given with an invite stays on its row when you switch organizations and come back. When the best and the lagging rep on the Quality card share a name but come from two CRM portals, each shows its portal. A failed read of the data source no longer says “not connected”: the banners and the Connection tab say the read failed, and Aelo retries once a minute.
- Voice of Customer: no false change from re-assigned themes. When the way themes are assigned changes, the comparison with the previous period no longer shows a change that comes from that rather than from the conversations; the screen says theme assignment was updated, and the lines draw a break. Pro and above.
- The Records list reads 5,000+. In a large organization the
organization-wide list stops counting at 5,000 and shows
5,000+; the public APItotalstays exact. - Demo data no longer goes blank as it ages. Role dashboards, the demo card and the embedded dashboard say when the demo data ended. A freshly seeded demo call now shows the canonical quality score, and its criteria and script answers follow it.
- Smaller fixes. The compliance settings show the saved consent mode, jurisdiction and legal basis instead of the defaults. Coaching notes and sessions say when a list failed to load and offer a retry, and filter notes by rep beyond the latest 50. A criterion template asks before replacing an answer type or “what we look for” edited by hand. After a refused or failed re-check, the note that a marked call was re-analyzed and the check must be run again stays on screen. In Settings, the AI assistant block (Pro and above) no longer stops at “Switched off at the platform level … You cannot turn it on from here — contact support” after a mismatch: the state is asked again, and when it cannot be confirmed the block says “Could not confirm whether the assistant was switched off at the platform level. Turning it on may not take effect.” and offers Retry. In Bitrix24 the locked Assistant button appears only when there is something to ask about.
One person one row in the Agents tab and the digest, two checks back, and an access log of real events · 26.56
- The personal-data check is back. The built-in criterion Broke personal data rules runs again in Analysis Setup → Criteria for organizations with a concrete jurisdiction. Its wording changed: an ordinary call about an order to the person who accepts it — greeting by name, reading back the order, amount, city, pickup point — no longer counts. It counts asking for card secrets or an SMS code, and naming the customer’s full name, address, pickup point or phone after the person who answered said they ordered nothing, before finding out who they are.
- The satisfaction-guarantee check is back, and asks only where a guarantee fits. The built-in criterion Explained the satisfaction guarantee applies only when the customer asks directly whether they can return or exchange the item, or says they fear it will not suit. Questions about features, compatibility, size, price or availability, turning down a purchase for other reasons, service, delivery, order status and payment show Not applicable, not “not explained”. A short confirmation from the employee to a question about a return or exchange (“yes, of course”) counts as an explanation; a time limit or conditions are not required. Organizations that already use built-in criteria get both checks back during the day of this update.
- The access log shows real events. Settings → Organization → Access Log lists who changed whose access in your organization, and when — members added or removed, role changes, analytics access, project assignments and org-structure changes — newest first, with a filter by type. Owner and Admin. Events are kept for 365 days. The log opens even when the general organization settings fail to load, and every time you open it, it reads the events afresh, so a change you have just made is already there.
- An invitation that carries access, and the page of a pending member. An invitation with With limited access now shows that access in the Access column of Team at once, without waiting for the list to load; when your role cannot give access to a person with this role, the refusal says exactly that; and after an upgrade to Pro, the option opens without reloading the page. A Group lead can open the page of an employee of their department who has no Aelo account yet (a pending member), when the CRM is connected through one portal; a namesake from another CRM stays closed. Pro and above.
- One person, one row in the ranking and the digest. The team ranking (the Agents tab) and the “best agent” and “at risk” lines of the supervisor’s digest follow the rule of the employee tables: an employee whose calls sit under their CRM id and under their Aelo account is one row with the summed score and calls, named after the Aelo account. The digest reads its own closed period and the recipient’s projects, so its names can differ from a ranking for another window. An employee without an Aelo account is kept apart per CRM portal: without a link to an account each portal keeps its own row, so the same id in two portals is two rows. In the Team tab, two rows with the same name now carry their CRM portal after the name, so a supervisor can tell whose calls the row holds.
- An employee’s page opens the calls of the right portal. The ranking and its trend cards link an employee without an Aelo account together with their CRM portal, and the page — score card, recent calls, category mix, team baseline and coaching tips — reads only that portal’s calls: the same id in two portals is two people. A person linked to an Aelo account opens as before, with all their calls.
- The “By manager” table of a criterion report is one row per person. An employee whose calls sit under their CRM id and under their Aelo account is one row with the summed answers; one without an account is kept apart per CRM portal, and rows with the same name show their portal. A number in a row folded from several ids is plain text rather than a link, because the call list filters by one id and would open fewer or other calls than the number says.
- Voice of Customer: a “no for now” is a decline even with a visit or a quote. A customer who turns the offer down for now and still accepts a visit, a meeting or a quote (“we don’t need it now — but come by, show us”) is counted as a decline with its reason. Only conversations analysed after this release are read this way. Beta, Pro and above.
- Voice of Customer: a summary card’s line keeps up with its number. When the number comes back changed while the card’s section is closed, the line no longer shows the old data — it returns with the section’s new answer. The objection card now says in words that its line is the share among all analysed conversations. Pro and above.
- Emails say how to change the address. The footer of the email about an analysis pause and of the one about 80 % of included minutes used now says where the address the email was sent to is changed, as the money notices do.
- Fewer calls marked “The call category is ambiguous”. When the call category is in dispute, Aelo now finds the quote that settles it in the transcript word for word, so a category is no longer left ambiguous just because of how the quote was worded — and the CRM update that waited for it goes through. Only calls analysed after this release.
- Better speaker separation. When speech recognition merges the two speakers of a call into one, Aelo can run the recognition once more and keep the split dialogue if it is better. The retry costs you no extra minutes. Calls already analysed are not redone.
- Uspacy privacy notice and processing instruction 1.21. They now give fixed periods for the call-event log (90 days) and the intake receipt (30 days) instead of the organization’s retention setting. An installation on 1.20 keeps working; its Uspacy card in Aelo settings asks you to reauthorize with the current texts.
- 14 days of Pro on the free plan. On the free (Pay-as-you-go) plan, your next analysed call or chat opens every Pro feature once, for 14 days — Voice of Customer, the AI assistant, deal state and more. Minutes, the price per minute and plan limits stay as they are, and during the trial the AI assistant takes up to 3 questions a minute, 15 an hour and 30 a day. A banner shows how many days are left, and menu items the trial opens read “Pro · trial”. When the trial ends, what it already produced is kept but the Pro screens close again; new conversations get no Pro processing. With an active Uspacy installation, the trial starts once its current processing instruction is confirmed.
- CRM fields in one table. For Bitrix24, Analysis Setup → CRM Updates lists every result Aelo writes into a CRM card — summary, scores, compliance — one row each: pick a CRM field, the Aelo default field or “Don’t write”. A row warns when the chosen field is missing on a card type or has the wrong type. The report, the transcript, activities and auto-fill sit in one list of actions, and Sync CRM Users moved to Team → Org structure.
- A Bitrix24 smart process gets its own table. Delivery to a smart process now writes only the results switched on there. With the default settings the summary, the quality score and the sale probability keep being written; the sentiment and the component scores are written once you switch them on.
- Score and compliance fields in the Bitrix24 card fill in. The seven score rows now write the call’s component scores — greeting, needs discovery, objection handling, closing, politeness, clarity, CRM — as on the record page, so card fields mapped to them start to fill. The recording-disclaimer, TCPA and data-privacy fields take the answer of the built-in criteria (a Yes/No field). A call without a sentiment score no longer writes “neutral”.
- Conversation themes in the Voice of Customer export. The Conversation themes block (beta) now goes into the CSV and the printable report of the Sales and Site and content tabs, with the same rows as on screen. Pro and above.
- An objection reason can be “new” again. In What changed on the Sales tab of Voice of Customer, a reason is marked new when no earlier period with recognized objections held it and no earlier period held an objection that could not be sorted into a reason. Pro and above.
- One person, one row. An employee whose calls sit under their CRM id and under their Aelo account is now one row with the summed numbers in the employee tables, the call statistics, the quality and script reports, the ranking, the digest and the Team tab. Two people with the same name stay two rows — nothing is merged by name. An employee without an Aelo account is kept apart per CRM portal until they are linked to an account.
- Script steps move, and a deleted one can be brought back. The up/down arrows of a script step now work, and the order moves on screen at once. A deleted step or phrase turns into an Undo line for 5 seconds.
- Money notices always arrive. Auto-recharge failure, budget threshold and negative-balance emails always reach the owner and the admins, whatever the email settings say; Settings → Notifications says so, and the email footer names where its address is changed.
- Operational logs are kept for fixed periods. The intake activity log is kept 90 days and in-app notifications 180 days; older entries are deleted automatically, except the entry of a call still waiting to be processed.
- A department head sees a subordinate’s analysis. Opening a subordinate’s call through the org structure shows the analysis even where notes are not available to you. Note, Edit and Delete appear only to whoever may write them.
- “Employee used profanity” counts only the employee’s lines. A “yes” backed only by the customer’s line no longer counts, and a line of an unknown speaker on a recording without roles gives “not sure” instead of “yes”.
- Routing rules in order. A new routing rule created without a priority is placed at the end of the order instead of in the middle. Rules that shared one priority are renumbered 10, 20, … in the order they already ran in, so the order itself does not change. Analysis Setup → Distribution now shows the rules in the order they are checked, and dragging a block moves only that project’s rules.
- Deep links to a moment. Opening an already open record at another moment — from a CRM tab or an assistant quote — pauses the player and moves to that moment.
- The Bitrix24 app signs in once more. After this update, an Aelo tab that was open in Bitrix24 signs in again once; if it asks, open it again from the CRM.
- Pausing an installation stops everything. A call already in processing stops before its next step, waiting calls are not started or re-analysed, and nothing is written to the CRM or sent as a signal while processing is paused or withdrawn. After you resume, start the waiting records from Aelo; an already paid transcription is not charged again.
- A menu on the app page. The Aelo app page in Uspacy is a menu of big buttons into Aelo — Records, Overview, Deals, Analysis Setup, the AI assistant, Settings and Billing.
- Demo data on locked Pro screens. On a plan below Pro, while your organization has demo data and no real conversation yet, Voice of Customer and Deals open filled with that demo, under the banner “This is demo data”, instead of a lock — you can see how they work before your own calls arrive. The banner has a See plans button (or a note to ask the account owner). Whatever writes or calls a paid model stays closed and says “Available on {plan} and higher plans”: the FAQ draft, editing the theme set, the draft message to the client, the CRM task and the Sales methodology button. Export works.
- Checks moved from the profile to criteria. Mandatory phrases, profanity and the recording disclaimer are no longer in the analysis profile: the built-in criteria in Analysis Setup → Criteria do these checks now. The profile switches for them are gone, and the Highlights tab no longer lists them among the frequent problems of new calls. Past calls keep the results they have. The alert preset Profanity detected (any speaker) is removed — Employee used profanity stays. The personal-data check stays paused until a new wording is measured, so for now no organization has one.
- Objections in the Sales export. The Export menu on the Sales tab of Voice of Customer now also exports Objections — the market’s reasons in the screen’s order, each with its conversations, its share and the previous period — as a table, a printable report and customer wordings. The file has no employee names. Pro and above.
- Coaching sessions follow your retention period. Sessions are now deleted together with other data once they are older than your organization’s retention period; a session scheduled for a future date is never deleted before it takes place, and a date more than 365 days ahead is refused.
- The retention window names everything it deletes. When an Owner shortens the retention term, the confirmation now lists not only records but also supervisors’ notes about employees, coaching sessions, AI assistant questions not tied to a record and deal states. If the count cannot be read, the term is not saved.
- Routing rules for a project’s own roles. A Supervisor who is an Admin of a project reorders that project’s routing rules (it used to be refused with an error) as long as only that project’s rules need new places — moving rules of other projects needs access to them too — and a member of a project reads its delivery and routing rules. Rules of equal priority now run and reorder in one order. When the default project is outside your access, the screen says so instead of naming it.
- Funnel stages named by the record’s own CRM. If two CRMs are connected, the stage in a record’s badge, in Voice of Customer (decline reasons by funnel stage) and on the Conversion tab is named from the list of the CRM the record belongs to — these screens used to read the first CRM’s list only. Where the Conversion tab shows several CRMs, each stage is prefixed with its CRM. A stage whose name could not be read, or that belongs to a replaced portal, shows “Unknown stage”, and the screen says that some names could not be read. A call series is joined only within one CRM installation.
- Notification settings show only what works. The In-app switch is gone — in-app notifications are always on. The Collaboration category and a manager’s feedback in “What you receive right now” appear only while coaching is on, and the summary no longer counts Telegram when only personal feedback reaches you. A role without shared categories still sees the channels that are already on, so they can be switched off. Your own address is asked under the Personal emails switch when the account has none or one is saved, and the footer of a feedback email names that switch.
- Theme filter in Voice of Customer, edges. On Site and content without customer questions, a theme from a link that is archived or no longer in the set is cleared with a message, and a refused theme is cleared together with its row. The themes block stays on screen when the filter does not narrow the tab. An FAQ draft built under a theme is no longer shown once that theme’s definition changes.
- Emails to your own address. The test of the Email channel and the billing emails (auto top-up, budget and balance) no longer go to the placeholder address of an account created from Bitrix24; with the Email channel on, billing emails go to the address you set.
- Voice of Customer pages start over. After you change the period, project or flow, the Marketing and Product blocks open from their first page.
- Forbidden words are a built-in criterion. The check moved from project settings to Analysis Setup → Criteria as the built-in criterion Employee used a forbidden word. The Owner keeps one list for the organization — up to 100 words or phrases — in the criterion’s panel and chooses the projects, channels and categories it applies to. Any form of a listed word counts, and only the employee’s lines are checked. While the list is empty the criterion stays paused. Like the other built-ins, it is outside your plan’s criteria limit; the forbidden-words alert now fires on it.
- “Client No-Answer” apart from “Missed”. In Records and in search results, the badge of a missed call now says whether it was an inbound call nobody picked up (Missed), an outbound call the client did not answer (Client No-Answer) or a missed call of unknown direction.
- Personal emails for every role. Where coaching is on for your organization, a manager’s feedback on your conversation now belongs to the Collaboration category, which every role sees in notification settings, and every user — an employee included — can turn its email off with the Personal emails switch, separately from the general Email channel. If your account has no email address (an account created from Bitrix24 can have none), the settings say so and show where to enter one.
- An answered call without a recording is no longer “missed”. When an answered Uspacy call never received its recording, it now counts under No conversation recorded rather than as a missed call.
- Built-in criteria in your criteria list. Up to seven checks worded by Aelo — company named, next contact agreed, call recording disclosed, satisfaction guarantee explained, employee profanity, TCPA on outbound sales calls (US) and a personal-data violation — now appear in Analysis Setup → Criteria in their own Built-in section, outside your plan’s criteria limit and inside the per-minute price. The Owner can pause them or narrow where they apply; their answers show in the call panel and PDF, the records filter, the Highlights tab, alerts and the report written to your CRM. The analysis profile switches they replace now open the criterion.
- The reason behind a “no for now”. When a customer turns the offer down for now and names a reason together with a later time, Voice of Customer records the reason: “no money now, call me in spring” is “budget”. “We don’t need it now” with no word that it will be needed later is “no need now”; “not now” is kept for a customer who will come back to buying later. This applies to conversations analysed from this release on, so against earlier periods “not now” falls and “budget” and “no need now” grow — on the Sales tab and in the monthly Voice of Customer email. Pro and above.
- Supervisor notes follow your retention period. Notes about an employee are now deleted once they are older than your organization’s retention period, counted from when the note was written.
- Refresh the Aelo tab in Bitrix24. The tab in a deal, lead, contact or company card has a Refresh button that rereads the card’s conversations — and, on a deal or a lead, the deal state (Pro and above) — without reloading the card, and says so when a refresh fails.
Manager feedback for the employee, Voice of Customer over time, and a Uspacy task for the responsible employee · 26.51
- Manager feedback reaches the employee. When a supervisor, an Admin or an Owner leaves a coaching note, an annotation (not a correction of the model) or the first comment on a review about someone’s call or chat, that employee gets a notification in Aelo and an email, and in Bitrix24 a notification in the portal. The link opens the conversation — for an annotation on a moment of a call, at that moment. The email carries no feedback text and no customer data; several comments by the same person on one conversation within 30 minutes send one email, and everyone can switch the email off in notification settings. The coaching workspace is now available in every plan.
- Voice of Customer over time. Every row of decline reasons, frequent questions, themes, competitors, market signals and product feedback carries a line of its share across the period; open a row for its bars by day or week, or for the last 12 months. Objections get the line and bars only in the market view on Sales. What changed lists the rows that grew, fell, appeared or disappeared against earlier periods. In the web app and in Bitrix24. Pro and above.
- The Uspacy task goes to the responsible employee. Create task in CRM now assigns the planned activity to the employee responsible for the deal or lead in Uspacy; where Uspacy shows none, or the organization has confirmed only an earlier version of the Uspacy processing instruction, the activity is created without a responsible employee and Uspacy assigns it by its own default. With no confirmed instruction that covers tasks, no task is created. Pro and above.
- The AI assistant has two separate switches. The Owner’s choice in Settings → Organization → AI assistant (Pro and above) no longer overwrites, or is overwritten by, a switch-off made at the platform level: the screen says whether the assistant is switched off by you or by the platform, and rereads your choice every time you open it.
- The Uspacy app shows how calls are analysed. The app page in a Uspacy portal says whether calls are analysed automatically, wait for a start, are only transcribed or are not processed.
- Aelo inside the Bitrix24 card. A deal, lead, contact or company card in Bitrix24 now has an Aelo tab with the card’s calls and chats; each one opens its full report right in the tab. On a deal or a lead the tab starts with the deal state, and a deal also lists the conversations of the lead it grew from. Everyone sees only what they may open in Aelo. The deal state is on Pro and up; on other plans the tab still lists the conversations. The tab comes with a new installation of Aelo by a portal administrator; on a portal where Aelo was installed earlier, it is not there yet.
- Create task in CRM for Uspacy. The button in the deal card now writes the next action into an Uspacy deal or lead too: one planned activity with the next action as its title, the reason and a link to the card in its description, and the due date as its time. A second click does not add a duplicate. It works while the portal’s processing is active under the current processing instruction; otherwise the card says why the button is inactive. Pro and above.
- Service status. Settings → Organization → Service status shows Owners and Admins how your conversations move through processing: the analysis mode, what is in the queue and how long the oldest record has waited, what was received, finished and stopped over 7 or 30 days, and the latest stopped records with the reason in plain words and a Retry button — without writing to support. Admins limited to some projects don’t see it: it covers the whole organization.
- Your own weights for the quality score. In a project’s settings, give each of the six quality criteria a weight from 0 to 10, and the quality score counts what matters most in that project — in the call card, the lists, the dashboards and ratings, digests and the CRM field. Until you set weights, every criterion counts equally.
- One theme across Voice of Customer (beta). The All themes selector narrows every tab of Voice of Customer to the conversations of one theme, and the files you export carry the theme in their name. Pro and above.
- A “not now” counts as a decline. From this release, a customer’s no to the offer counts as a decline in Voice of Customer even when it is only for now (“no money this season”, “call me next year”), with “not now” or “budget” as the reason; “I’ll think about it” without a no stays postponed. Conversations analysed before the release keep the earlier reading, so declines — most of all “not now” and “budget” — grow against earlier periods. Beta.
- Remarks on a report show their evidence. A fact-check remark on the report’s wording now quotes the words of the conversation behind it, unless that quote held personal data and was removed. Remarks that only claimed something was never said are gone, also from conversations analysed earlier: fewer remarks, each one you can check.
- The AI assistant catches more personal data. An address spelled out in words, a date of birth or a card number split between turns is now found by an extra AI check and masked in your question, in the conversations the answer is written from and in the answer itself. Answers take a few seconds longer.
- Plan & Billing names each figure’s window. Minutes left now, Minutes used this plan cycle and Budget left this month each say which period they count, and the included-minutes emails say “this plan cycle” on a paid plan.
- A short call without analysis spends no minutes. A call too short to analyse is no longer charged against your included minutes.
- Short calls in the funnel are counted as “too short”. Calls Aelo classifies as short now count as too short instead of no recording in the funnel and the call series, so a comparison with an earlier period shows a step.
- Voice of Customer, one filter bar on every tab. The same filters and one Export menu on every tab, Sales included; long lists in Marketing and Product and service show ten rows at a time with Previous and Next, and exports still carry every row.
- The sales methodology has its own setup step. Analysis Setup → Sales methodology, also opened from Deals, shows how many of your funnels are configured.
- Access you take away applies at once. Removing someone from a project takes effect immediately: each new request, including a new download of a recording, is checked against their current access.
- Deal advice that uses all your answers. The deal state and the draft message to the client now get the approved answer to every objection still open in the deal, however long your company rules are.
- Which script steps the team skips. Analytics → Script steps shows, for every script, the share of conversations where a step that applied — every required step, and an optional one that came up — was not completed, how many were half done, and the breakdown by employee and by the step’s criteria. One click opens the conversations where the step was missed. A step that applies only in some conversations is best marked optional. For Owners, Admins and Supervisors (their projects), in the web app.
- Conversation themes in Voice of Customer (beta). Keep your own set of themes — a product model, a service, a delivery region — and new conversations get up to three of them (with customer questions switched on). The Sales and Site and content tabs count them, with the quality score, declines and unanswered questions per theme. Start from a proposal built from your last 90 days; once a week Aelo suggests new themes that came up often enough, for you to accept or reject. Pro and above.
- Criteria without a blank page. Start from a template offers ready wordings — an additional product offered, the budget clarified, the next step named and more — or Describe in your own words and Aelo drafts the criterion and tests it on 20 recent calls. Mark an answer The answer is wrong, and Suggest a fix proposes a better wording, shown before and after.
- A first draft for the client. Draft a message to the client in the deal card writes a short follow-up from the deal’s current state — the next step, the open objection, what was promised — in your sales methodology and the project’s language. Check it, edit it, copy it; nothing is sent or written to the CRM. Pro and above.
- Features above your plan are visible. Deals, the AI assistant and Voice of Customer now show in the menu with a lock and the plan they start from; opening one shows what it gives and where to upgrade.
- Switch the AI assistant off yourself. The Owner turns the assistant off for the whole organization, and back on, under Settings → Organization → AI assistant. Pro and above.
- A card that reads top down. The deal card goes verdict, next action, grounds, history; the deal list shows on every row why the deal has its status (to those who may read conversation text), the chance to close and the next action with its due date.
- A converted lead continues as its deal. When a lead becomes a deal, the deal starts from what Aelo already knew about the lead, and the card links back to it. Bitrix24 and Uspacy.
- Stage phases from your own stage names. Aelo’s AI reads the names of your pipeline stages, in your language, and suggests each one’s phase on the Deal Stages tab; your own choice always wins, and one click keeps the suggestions. With stage-based evaluation on.
- Deal funnels, outcomes and stages. The Deal Stages tab lists your Uspacy funnels, each with its own sales methodology, and the deal state follows the funnel of the deal. With stage-based evaluation on, the Sales tab shows won and lost Uspacy deals and whether a call moved its deal forward.
- Voice of Customer in layers. The Sales and Site and content tabs open with summary cards — on Sales the top objection, decline reason, question and theme; on Site and content the most-asked questions and the theme with the most unanswered ones — then one section at a time, each list with its first five rows.
- The attention flag shows its moment. Under the flag’s reason the call’s analysis now shows the moment it rests on — time, speaker, quote — and the alert card does too. A customer who is only comparing offers no longer raises a high flag; one who is leaving for a competitor still does.
- Fairer greeting scores on inbound calls. On an inbound call the greeting counts identifying and confirming the customer’s request, and using the customer’s name only once the name is known. Inbound greeting scores rise from this release, so a period comparison across it shows a step.
- Missed calls counted one way. Call statistics and Missed calls cover calls only and share one definition of the missed share; missed calls have their own row in the funnel and their own Status filter in Records.
- One quality score in the email and the webhook. The analysis email and
the webhook report the same 0–100 quality score as the call card, the
dashboard and the CRM field. For webhook integrations: the
average_scorefield keeps its name but now carries this quality score instead of the average of every numeric metric, and a call without a score sendsnullinstead of0. - One look across the app. Every screen shares one header with breadcrumbs and actions, and text follows one type scale.
- A demo that shows every report. Demo data now fills the Script steps report, Voice of Customer with its themes, the Sales tab and the funnel.
Our largest release so far. From this release on, version numbers start with the year: 26.48 follows 2.47.
- Deals: what to do next, deal by deal. After every analysed conversation linked to a CRM deal or lead, Aelo updates the state of that deal: At risk, Needs attention or On track, the chance to close and what changed, why, the next action with its due date, and what to say at the next contact. Deals in the menu groups them, with their amounts from Bitrix24; the deal card keeps the history of states and the conversations behind them. Each new state also lands in the CRM as a separate comment in the deal’s timeline (Bitrix24 and Uspacy; on by default, only for conversations up to 7 days old), and in Bitrix24 the next action becomes a CRM task in one click. The advice follows the sales methodology you set for each pipeline — BANT, SPIN, MEDDIC, Challenger, plus your own rules. Pro and above, in the web app.
- Voice of Customer. What customers say across a period, split by who acts on it: Sales (objections, questions, decline reasons), Marketing (competitors, prices, demand, needs), Product and service (incidents, issues, praise) and Site and content. Every row opens the conversations behind it; tables, a printable report and customer wordings export for people who don’t use Aelo, and a monthly email brings the previous month’s summary. For Owners, Admins and Supervisors (their projects). Pro and above.
- Customer questions and decline reasons (beta). Inside Voice of Customer: the questions customers ask most, by subject; the ones left without a full answer; what they ask in the first minute — what they could not find before calling; and why customers declined, broken down by call number, employee and funnel stage. Build a draft turns the frequent questions into an FAQ draft for your website. Collected from conversations analysed from this release on. Pro and above.
- Call criteria of your own. Write the questions that matter to your business — “Did the agent offer delivery?”, a 0–100 score, or a choice from your list — test the wording on your last 20 calls before saving, and every new conversation is checked against them within the usual per-minute price. The Criteria tab of the dashboard shows each criterion by period and by manager, the Records list filters by criteria, and the Bitrix24 app shows the answers and the report too. Every plan, up to its criteria limit.
- Alerts on a criterion. An alert rule can now fire on a criterion — it triggered, its score, the chosen option — and the alert in the app shows the quote from the call that raised it. Notifications by email, Telegram or webhook do not carry the quote.
- Ask about all your conversations. The AI assistant now answers questions about every analysed call and chat you are allowed to see, not only one call or one deal. In the web app it lives under AI assistant in the menu: narrow a question by period, project, agent, type, category or customer. Inside Bitrix24 it opens from the Assistant button, without filters. The answer quotes the conversations it comes from and says how many it searched; in a large base it may search only the 5,000 most recent matching conversations, and the answer says so. It is prepared in the background and can take a few minutes. Pro and above.
- Narrow analytics access. Give a Supervisor or an Agent exactly the analytics they need: Analyst sees section totals only — no records, quotes or audio — for the whole organization or chosen projects; Group lead sees everything about the departments you pick, including their calls and scores. Set it in the web app under Settings → Team & Access or right in the invitation. Screens and notifications follow the access, and the assistant over all conversations is not available with it; the role, projects and billing rights stay as they are. Owners and Admins assign it. Pro and above.
- Aelo fields on every card. Aelo creates its fields on deal, lead, contact and company cards — wherever reports are delivered — and the score on a card is the latest analysed call’s: an older call processed later never overwrites a newer score.
- Fewer duplicates in the timeline. A separate timeline note for each report is now off by default; turn on Add Timeline Note in the delivery settings if you want it. With it on, an open-line chat’s report is added to the chat’s own activity, the way a call report sits on the call.
- A deal phase for intermediate stages. Where stage-based scorecard selection is on, calls at intermediate stages get a phase too — the one you choose on the Deal Stages tab, or else one guessed from the stage name and marked Guessed. Changing a stage’s phase moves the calls already recorded there.
- Records remember your filters. Leave for the dashboard and come back to the same view; Hide short calls clears the list of calls too short to analyse. In the web app the Status filter speaks the funnel’s language, and a funnel row on the dashboard opens Records filtered to exactly what it counted.
- Every flagged conversation within reach. Flagged for attention on the dashboard no longer stops at the first 50 — Show more loads the rest.
- The price before you analyse. In manual analysis mode, Analyze on a single record shows the price first and never charges more than it showed. A record that failed says at which step and offers to try again.
- Yesterday’s unhandled objections in the daily email. For Owners and Supervisors: up to five reasons the team left unanswered yesterday, with counts and a link to the Objections screen.
- Analysis setup at a glance. The Analysis setup overview shows a record’s path — source, steps, result — and what still needs your attention.
- Your week, your language. An organization can choose the first day of the week for dashboards, weekly charts and digests (Monday by default). Script templates you haven’t edited follow the organization’s language.
- “Owner” instead of “Client”. The organization’s top role is now called Owner everywhere, including invitations.
- Long chats. A chat too long to analyse is kept and shown with the reason, and is not charged.
- A deleted record is cleaned up to the end. Once a record is deleted — by hand or when its retention period ends — Aelo keeps retrying until its transcript, analyses and audio are gone from Aelo’s database and audio storage. Copies already delivered to your CRM stay there.
- Safer notifications. Telegram receives only the notification types that are safe for a chat, without caller contacts, and the channel settings say so.
- Easier to read. Text and buttons meet accessibility contrast, controls share one height, and labels, money and scores follow the interface language.
- Objections in full, not only the dropped ones. On the dashboard’s Quality tab, All objections → opens a screen with the objection reasons your customers raised in the period — how often, in their own words, with quotes that open the call, the team’s best replies taken from real conversations and the change against the previous period; objections that fit no reason and older wording that could not be recognized are shown as separate shares. For Clients and Supervisors (a Supervisor sees their projects); in the Bitrix24 app it opens inside the app.
- One quality score everywhere. The score in the records list, its filter and the record card now match the dashboard: the mean of the conversation criteria the analysis rated (up to six), with one decimal. Ranges such as 0–79 and 80–100 meet without a gap.
- The budget shows what you are charged. “Used” and “remaining” on the dashboard and in Settings → Plan & Billing → Budget are now your usage charges for the budget period — the same amount the threshold notifications use. The budget never pauses analysis.
- Supervisors start with their own projects. With no project selected, a Supervisor’s dashboards, leaderboards, reports and digest cover the projects they supervise, and several can be picked at once. These views cover the projects a Supervisor is assigned to — assign them in Settings → Team.
- Leaderboards and trends cover the whole team, not the first 20 agents, and Highlights examples open in place.
- Bitrix24: search on the Records tab now finds records, as in the web app.
- Chats read by name. On the record screen, a Bitrix24 chat reply shows the sender’s name, and quoted text is muted.
- Your language, your formats. Dates, the time-zone offset, the currency sign and labels follow the interface language.
- Script scoring status is clear. While script adherence scoring is off, the script settings say so instead of showing the rules as active.
- Privacy. A phone number, e-mail, card or IBAN split between two speaker turns is now masked, and a deleted project leaves reports and search usually within half an hour instead of days.
- Your organization always keeps a Client. Only a Client can change or remove another Client, and the last Client cannot be demoted or removed by anyone, themselves included. On the Team screen a protected Client has a badge instead of the role menu and an inactive remove button — hover over either to see why.
- A quote in an open-line chat is no longer the sender’s words. When a Bitrix24 open-line message quotes an earlier one, the transcript shows the quote as [Quote] «…» — on screen, in exports and in the CRM — and the analysis no longer attributes the quoted words to the sender. A message that is only a quote is not counted as a reply.
- Assistant questions and answers follow your retention period. A question and its answer are deleted when the record asked about or any record the answer was built from is deleted — usually together with it, otherwise by a routine cleanup — and in any case at the end of your organization’s retention period, including questions whose answer failed.
- Sale probability, clean and on scale. The sale probability sent to your CRM and the API no longer carries rounding noise (55, not 55.00000000000001), and when the analysis returns a value off its scale, the field is now left empty instead of guessing what it meant.
- Search finds your records however many others match. In a large organisation, a search in the records list of the web app could stop before it reached the records you can see when thousands of others matched first. It now keeps going until it finds them, loading more as you scroll, with a Search further button when a long search needs another step.
- You’re told when search runs in a simplified mode. In the web app, if part of the results came from our backup search, a note above the list says some records may be missing and suggests trying again in a minute.
- Ask the assistant about a whole deal. When a call or chat is linked to a deal, lead, contact or company in your CRM, Ask about the deal (or the lead, contact, company) in the record header answers from its conversations you can see — the ones most relevant to your question in full, and it tells you when a long history had to be shortened. Quotes come with it, and a click on a quote from another conversation opens it. The history of your questions about the deal stays with the deal. Available on Pro and above.
- Search finds names whatever the letter case. In the records list of the web app, “олег” now finds “Олег” — search no longer depends on capital letters in Cyrillic.
- “Analysed” means analysed. The number of analysed conversations on the dashboard cards now counts only calls and chats that actually have an analysis — missed calls and calls too short to analyse are no longer included, so it may be lower than before.
- Fairer analysis of your agents. The analysis now checks who actually said a line before holding it against the agent, so the client’s words — including swearing and mistakes — are attributed to the agent far less often.
- Handled objections stay on the card. The “Objections the team drops” card also lists objections your team handled in every conversation, at 0 % in a muted colour, so you see what comes up, not only what goes wrong.
- See what’s new right after an update. The first time you sign in after a release, a short window shows what changed — in your language, in the web app and inside Bitrix24 alike. It appears once per person, not once per browser.
- One competitor, one row, however it was spelled. On the Highlights tab, competitor names are merged through your glossary: “Lemken”, “lemken” and the same name in Cyrillic become one row, and a conversation that mentioned both spellings counts once. Your own brand, the platforms you service, suppliers, partners and colleagues from the glossary are never listed as competitors. Once your glossary lists at least one competitor, a name it doesn’t know yet is marked “not merged”, and under the list you see what share of the names heard that is, with a few examples — send those spellings to support and they merge, past conversations included, without re-analysing anything.
- The assistant panel keeps up with you. It names the record it is answering about right under its title, and when you open another record it moves there with that record’s own conversation and draft. An answer that is still being prepared is never lost: the panel waits for it, then offers to move over.
- Install Aelo straight from the Bitrix24 Marketplace. Aelo is published in the Marketplace, and the connection wizard, the integration page and the installation guides now open its card directly.
- Ask a question about a call and get an answer you can verify (beta, Pro and above). Open an analysed conversation and ask what you want to know about it — what the customer objected to, what was agreed, whether the agent followed the script. Where the assistant can back a thesis with this record’s transcript, the quote is shown under it: pinned to one place in the recording, it carries a timecode that moves the player to that moment; unconfirmed, or found in several places, it is marked as such instead of being passed off as verified. A thesis it cannot back stands without a quote rather than with one that only looks like evidence. Nothing has to be taken on trust. For now the assistant answers about the one record you have open. Included from Pro upward and on there by default; if you would rather it stayed off, the organization owner can switch it off in Settings → Organization. Conversations with the assistant are kept for up to 365 days and are deleted together with the record.
- A Highlights tab that sums the period in plain words. On the client and supervisor dashboards: conversations from received to analysed, the three most frequent issues by scoring criterion, the conversations with no high or critical attention flag beside the list of the flagged ones, the average score with the best and the lagging agent, what the conversations were about, serious product complaints and competitor mentions. A supervisor sees only their own projects.
- Objections ranked by the reason behind them. Every objection is now sorted into one reason from a closed list of 19 — price, not now, delivery and availability, needs approval, and so on — so the same reason is counted together however differently customers phrase it. Objections analysed before the list existed are sorted through a stored mapping of past wordings; the share that could not be recognised is shown on the card rather than folded into the rest.
- A cancelled subscription no longer stands between you and a new plan. After a cancellation every plan card offered “Manage subscription”, the button opened a Stripe portal with nothing left in it, and buying a plan again was unreachable from the app. Plans are purchasable again, and the page no longer promises a cancellation for a period that has already ended.
- The delivery webhook says whether the fact check actually ran. Since 2.41
that pass is skipped when an analysis has no extracted fields and no
agreements — there is nothing for it to guard. The
verificationblock now carriesfact_checkbeside the status, so an automation can tell a skipped pass from a completed one.statusitself is unchanged: the new field is additive and safe to ignore. - A call transcript names two speakers, and “erm” is no longer counted as a word. Hesitation sounds are hidden in the text you read, and the speech score now goes by how often they occur per minute rather than by the raw total — a long conversation is no longer marked down for the same manner of speaking that a short one scores well for.
- Fact-checking now runs where there is a claim to check. This pass exists to guard the fields and the agreements an analysis sends to your CRM. With those switched off it had nothing to verify and reviewed the wording of the summary instead, marking two records in three as unverified over objections to how a sentence was phrased. When there are claims, the summary is reviewed alongside them; when there are none, it now reaches your CRM without that review. The safety review that runs on every analysis is unchanged.
- An objection whose quote had to be hidden for privacy stays visible. When a supporting quote contained something like an order number, privacy minimisation removed the quote — and the objection disappeared from the record and the printed report with it. The objection now remains, with its section and its reason; only the quote is withheld.
- A telephony source connected for audio only stays audio only. Where telephony supplies recordings for calls your CRM owns, its call history is no longer turned into a second set of records beside them.
- Speech recognition runs on a single provider. The original provider has been removed from the product, the sub-processor register and the credential store. Transcription is unaffected: the provider added in 2.6 has been the platform default since July.
- An analysis that could not be fully verified now shows you what it could not confirm. Where the panel used to report only that something was unconfirmed, it now names the status, the reason, and each specific claim: which section it came from, what kind of problem it is, and — whenever an exact quote can be found in the recording — the words that support it. The same appears in the printed report, so the reason travels with the record.
- The quote under “In the conversation” is the conversation’s own text. It used to be the wording the model produced; it is now a slice of the transcript, matched word for word. A quote that does not match exactly is not shown at all — the objection stays, with its section and reason, but nothing is put in someone’s mouth.
- The analysis report now always reaches your CRM. An analysis with an unconfirmed claim used to produce no CRM report at all, which left the salesperson with nothing instead of something qualified. The report is now published with a notice of what was verified and what was not.
- The script-adherence summary matches the breakdown beneath it. A step’s score follows the criteria that actually matched and the weights your script gives them; an optional criterion that did not happen no longer costs the step anything; a step with no criteria is left unevaluated instead of being marked failed; and skipped steps are named rather than left to inference.
- “Turn evaluation off” and “change the script” are now separate actions. The “Pin script” toggle promised behaviour the analysis never had, so it is gone, and the guides that described it have been corrected.
- No scores reads as no scores. An employee with nothing scored yet was shown “My Score 0/100” — a real evaluation of nothing. An absence now looks like an absence, on the headline, the trend, and the progress card.
- The analysis preview is computed for the project you are looking at, and shows the prompt the server actually built for it.
- Signing up and setting up your first project is one continuous screen instead of a sequence of separate pages.
- Fewer calls are written off as having no recording. A call now reaches the audio index before anything decides that no recording will come, and the waiting period is counted from the last time that index was written rather than from the call itself.
- Call duration is reported as a whole number of seconds, rounded once when the record is created — including in the public API, where the documentation now says so.
- A record halted because its source was disconnected can be sent back into processing. When an integration is disconnected, a call still waiting for its audio stops with that reason — and it used to be a dead end: you saw the reason and could do nothing about it. Reconnect the source and you can now return the record to processing from the record itself. The action appears only where it can actually help, and a failed attempt leaves the record exactly as it was.
- A quality sub-metric score is the score the rubric gave. Scores of 10 or below were being multiplied by ten, on the assumption they came from an older 0-10 rubric — so a genuine 5 out of 100 appeared as 50. We measured every scored analysis and found no trace of that old rubric, and 494 real low scores being inflated by it. Those analyses now show a lower and correct number. If you keep our scores in your own reporting, the values you pulled earlier for those calls will no longer match.
- A colleague is one person, on every screen that ranks them. An employee who exists in two connected systems — or under two ids in the same CRM — was counted twice in the ranking denominator, could have another person’s calls pulled into their card, and could appear at one position in the daily digest and another on the page that email linked to. All three now follow one rule, and coach notes are found by the person rather than by whichever id the request carried.
- Calls with no recording are no longer lost. A call whose provider mints the audio link later, or that a phone system never flagged as recorded, was being discarded on the way in without appearing anywhere. It is now ingested as a record. A message the platform does refuse now shows up in the Activity Log with a reason, instead of being visible only to us.
- A long or difficult call still produces an analysis. When the first attempt does not fit, the retry now keeps the model’s reasoning and asks for a more compact answer, rather than returning nothing.
- An agent’s quality score means the same thing everywhere it appears. The number on the agent’s own page, the one a supervisor sees for that same person, the metric columns underneath, the coaching summary and the digest email were each worked out slightly differently — different rounding, a different set of records, a different way of combining the individual criteria. They now follow one rule, so a metric marked as a growth area always sits below the heading it belongs to, and a record with no rubric is shown as unscored instead of as a zero.
- A supervisor and an agent see the same six figures. Opening a person’s performance from the team view and opening it as that person gave different answers for the same period — a different record set, a different rank denominator, no team markers on the supervisor’s view. Both views now read the same source.
- The report delivered to your CRM shows script adherence. If your organization has a script, the analysis already scored how well it was followed — but the manager reading the deal in the CRM could not see it. The timeline entry now carries the score, the steps, and the required phrases that were missed.
- The starter scripts a new organization receives now apply on their own. Four of the six are bound to the call categories they belong to; the other two are labelled as templates to adapt, both in the interface and in the documentation. Organizations created earlier receive the same bindings.
- Having the AI read your script no longer costs you anything. Parsing a script in settings runs on our account, with a fair-use limit per organization, and is excluded from your cost reports.
- Attachments in a chat are described in your language instead of as a service marker.
- Highlights and notes on a transcript stay where you put them. A highlight and a selection now cover the same unit of text, overlapping highlights no longer print a marker twice, and a note is stored against the original wording — so it survives a re-analysis of the conversation.
- “Total Transcripts” on the dashboard counts conversations. It counted rows, and a single call can have several — a cleaned-up version and a re-marked one both point back at the original. The breakdowns underneath the card now cover exactly the same set.
- A record that refused to be re-analysed can be re-analysed. Where the analysis version had drifted between the two stores behind the product, the record is repaired automatically instead of reporting an error.
- Telephony and Bitrix24 credentials are encrypted at rest. In 2.37 the keys for speech recognition, analysis and email delivery were sealed by the application itself. The same now applies to the credentials stored for your telephony provider and your Bitrix24 portal.
- Connecting a source recovers from a bad configuration. A malformed setting no longer breaks the connection, a tab left open explains itself instead of acting on stale state, and disconnecting affects exactly the installation you chose.
- Removing the Bitrix24 app finishes cleanly. An ordinary removal from the portal no longer reports an error, and the notification binding that tells us about it is restored where it had been lost.
- Chat analysis now knows which side sent each message. Who said what in an Open Channel conversation was decided by comparing the sender with the activity’s responsible employee — so a chat answered by anyone else could come out with the roles swapped, or be judged as though your side had never replied. The side now comes from the conversation itself.
- The price you are shown before starting pending records covers exactly the records that will run. A single run processes up to 200 records, and the card now says how many of the accumulated ones that price was calculated for; the confirmation step adds how many are left for the next run.
- Recognition confidence on the dashboard reflects what was actually measured. A call that had been cleaned up or re-marked counted several times over, and “not measured” was shown as 0.0%.
- What the AI parser produced is visible before you save it.
- Provider API keys are encrypted at rest. The keys stored for speech recognition, AI analysis and email delivery are additionally sealed by the application itself, so reading the database alone does not yield a usable key. The privacy policy and the DPA state it.
- Every script now shows its projects. The scripts page lists what each script applies to. A project where this script would never actually run — because the project is paused, or because another script is the one chosen there — is shown dimmed and moved to the end, and a script where every project is like that is marked Not assigned instead of looking like any other.
- The AI script parser keeps your script a script. Speech-quality notes (“confident tone”, “no filler words”) and instructions written for the analyst are recognized as such, left out of the steps, and listed with a short reason before you save — instead of quietly becoming criteria that duplicate what call analysis already measures.
- “How many minutes are left” is one number everywhere. The remaining included minutes on your subscription screen, the price quoted for pending records and for an import, and the limit analysis itself applies are now worked out the same way. Organizations that had moved between plans could previously see a figure calculated over a period that had already ended.
- The pause notice tells you the current state. Once you top up, or when a new cycle renews your included minutes, the banner stops saying funds ran out. If analysis was switched off automatically, that — and when it happened — is now visible under Settings → Organisation, not only above the records list.
- A record stopped for lack of funds says so. Previously such a record could come back as “not started yet”, hiding the actual reason.
- Analysis now has two named modes instead of an on/off switch. In Automatic, a new record goes straight into processing, as it always has. In Manual, a record waits and spends nothing until you start it. Set the mode in the banner above the records list or under Settings → Organisation — in the portal and inside Bitrix24 alike.
- Start what has accumulated: one record, a selection, or a batch of the backlog. The button is on the record card; the bulk start sits above the list. A single run takes up to 200 records and tells you how many are left for the next one. Before anything is charged you are shown what that run will cost, calculated record by record rather than from a total — and where a call’s length is not yet known, you are shown a “from” amount together with how many such calls there are, because their duration is only measured once the recording is transcribed.
- An empty balance is now one honest pause instead of a wall. Analysis moves your organisation to manual mode once, naming the reason and the moment, rather than marking every record “no funds”. Records held back this way can now be started like any other — previously they could not be started at all. Free organisations are not paused: their monthly allowance renews on its own.
- Topping up does not restart analysis by itself. What accumulated waits for you to start it, so a top-up never turns into an unexpected charge. The pause email, the notification and the FAQ all say this in the same words.
- The billing screen answers “do I have minutes?” first. Remaining minutes are now their own card and read as of today, independent of the period you are browsing. The plan’s allowance shows as a fraction — “0 of 100” rather than a bare “0” — what your spending was covered by is listed under covered, and the banner says which pool the current analysis is drawing on.
- Answered incoming calls reach Aelo sooner. Bitrix24 marks a call completed about a minute and a half after it stops reporting on it, and calls that arrived in that gap used to wait for the hourly catch-up. They are now picked up as soon as the call closes.
- A metric nobody measured no longer shows as zero. On an agent’s dashboard, a metric that does not apply to the channel — speech clarity in chats, for instance — now shows a dash instead of “0 out of 100”. A genuine zero, in turn, now appears in growth areas and coaching, where it used to be filtered out along with the placeholders.
- Photos and links sent in a chat now reach the transcript. A photo sent without a caption, and any message containing a formatted link, used to be dropped before analysis.
- Calls from Binotel now reach Aelo. Their webhooks are sent from the provider’s own network ranges, which the connection’s IP allowlist now recognises.
- A chat now draws half an included minute instead of a whole one. Twice as many conversations fit into the same allowance, and the point where analysis runs into an exhausted plan comes later. The price of a paid chat is unchanged: a chat beyond the included minutes still costs the flat per-chat rate.
- Telephony can now be connected as an audio source, from the wizard. Some CRMs register a call but never attach its recording. A telephony installation can now be switched into that role during setup: it creates no records of its own and instead supplies the recording the CRM record is missing. It appears under Settings → Data Sources → Connection as its own card, with its webhook URL and the prepared email for the provider’s support. Available today for Binotel alongside Bitrix24.
- The billing screen says what your minutes were covered by. One card for the period shows how the minutes split between your plan’s grant, your bonus and overage, with the amount charged next to the balance it came from. The transaction history filters across the whole period rather than the page in front of you, and loads more on request instead of stopping silently.
- A conversation with no recording now tells you why. Records whose audio never arrived used to say the recording had been received and stored. They now name the reason — a missed call, or a CRM that logged the call without a file.
- A self-served webhook secret can be read again after setup. Previously it appeared once, while connecting, and could not be recovered afterwards.
- The transcript can now be written into a CRM field you choose. The setting existed in field mapping, but delivery never filled the field. It works now — and it arrives switched off, because the field carries the full text of the conversation and that is your decision to make, together with the field it goes into. Nothing changes for Smart Process delivery: there the transcript already appears in the item’s timeline next to the analysis report.
- The company name you enter during Bitrix24 setup is now the name of your organisation. It was asked, checked, and then dropped, leaving the portal domain in its place. If you have already renamed your organisation yourself, nothing is touched.
- A chat with a transcript is analysed even when speakers cannot be told apart. Previously such a conversation could be closed as having nothing to analyse.
- A phone-system error is no longer read as “there is no recording”. Those are different answers, and treating them alike left calls waiting a day for audio that had already been offered.
- Shortening your retention period now applies to calls already on file, not only to those that arrive afterwards.
- Reconnecting a phone system keeps it as a source of audio if that is the role you gave it. Running the wizard again used to reset it quietly, and the effect showed up a day later.
- When your CRM registers a call but never stores the audio, Aelo can take it from the phone system instead. Some telephony integrations write the call into Bitrix24 but keep the recording on their own side — the card exists, the file does not, and until now there was nothing to analyse. A telephony connection can now be added purely as a source of audio: it stops creating its own records and simply supplies the conversation for the calls your CRM already has. Aelo matches the two by the call identifier your CRM carries, and failing that by number, time and length. Binotel is the first provider supported in this role.
- Processing your accumulated conversations now works from one button. Calls that arrived before analysis was switched on can be sent through in a batch, including those whose recording had not yet reached us. Before starting them, Aelo pulls your operator’s call log for the same period, so older calls can still be matched to their audio.
- A conversation that will not be analysed says so, and says why. Instead of a record that silently stays empty, you see whether the recording is confirmed absent at the provider, whether several calls matched and none could be chosen, or whether the audio never arrived.
- Chats now use your plan’s included minutes. A chat spends one minute of the monthly grant, and your wallet is charged only for what the grant does not cover. You can also set the minimum number of messages worth analysing — shorter exchanges are neither analysed nor billed.
- Every conversation now shows both times, each labelled. When the conversation happened, and when it reached Aelo — so the gap between them is readable at a glance instead of guessed.
- You can now subscribe to the newsletter, not only unsubscribe. Until now the only place to say yes was a checkbox during web sign-up — which nobody who arrives from a Bitrix24 portal ever sees. It is now offered in three places: at sign-up, once when a portal account is linked to a web account, and in Settings › Notifications, where the account owner or an administrator can turn it on and off at any time. It is separate from the alerts and digests about your own account, which keep arriving either way.
- Fonts are now served by Aelo itself. The interface, the website and the PDF report used to load their typefaces from Google’s font service, which meant your browser opened a connection to Google directly — before any consent banner had a say — and handed over your IP address and browser details. The fonts now ship with the product, so that connection no longer happens at all.
- The sub-processor registry describes telephony exactly as it works. It previously covered only recordings submitted through the public API. It now also spells out the two other ways a recording reaches us: providers Aelo polls using the credentials you configure, and providers that simply send us a link to the recording.
- A call that arrives without a webhook is picked up within minutes. When your CRM does not notify us — which, measured on live traffic, is how a third of Bitrix24 activities actually reach Aelo — the reconciliation pass used to run twice an hour, so those calls could sit for up to an hour before analysis even began. It now runs every five minutes, and the safety window before an activity is treated as final is two minutes instead of ten.
- Signing in to the web app from a Bitrix24 portal keeps you in your own organization. Bitrix24 does not share a user’s e-mail address with an embedded application, so opening the full web version used to create a new, empty organization around you. There is now a link from the portal that binds the account you sign in with to the profile you already have.
- A source whose authorization has expired is shown as disconnected, with the reason. It used to keep appearing as a working connection, so a portal that had stopped delivering calls looked healthy.
- Your team list matches employees by their portal identity. Under Bitrix24’s minimal permissions the e-mail address is not shared, so matching by address found nobody even when the connections were working correctly.
- Withdrawing consent for marketing e-mail now unsubscribes you. Previously the withdrawal was recorded, but delivery stopped only through the unsubscribe link in the message itself.
- An analysis that fails its automatic check now says so. The report
e-mail carries a note, and the delivery webhook a
verificationblock with the status and the reasons. CRM automation was already held back in that case; now the other channels tell you the same thing instead of delivering the report as if nothing happened. - The data retention window is editable by the organization owner. 1 to 365 days, with a preview of how many records a shorter window would remove and an explicit confirmation before it does.
- A phone number that arrives in a contact’s name is masked like a phone number. CRMs create a contact from an inbound call with the number itself in the name field; those now show the last three digits in e-mail and personal webhooks, as everywhere else.
- A disconnected CRM can be reconnected, and you are warned first. If your organization has two sources connected, both stay visible after a disconnection and each comes back on its own button. The warning that the portal tile goes dark now appears in the confirmation dialog, before the disconnection rather than after it.
- A chat that failed before it was analyzed can be re-analyzed. The button now replays from the recording itself rather than expecting an analysis that was never saved.
- Voice metrics say “not enough data” instead of showing zeros. When pitch or pause detection degrades on a recording, the card and the PDF report both say so, rather than presenting the zeroed values as a measurement.
Three languages instead of one, chats on equal footing with calls, and every analysis double-checked · 2.27
- Report language and recognition language are now two separate settings — and both default to Auto. The report is written in the language of the conversation, and the recognizer detects the spoken language on each recording, so a project no longer inherits a language from the screen you happened to be using. Set a fixed report language per project from the Analysis Setup hub when you need one; pick the recognition language from 90+ supported languages with search. Quotes from the conversation are never translated.
- Chats are analyzed on the same footing as calls. A chat used to land in the catch-all category with no scores and no alerts. It is now categorized into the same ten categories as a call — from the whole conversation, not the first few messages — and scored with chat-appropriate criteria, so analysis profiles, script rules, scores and alerts apply to chats too.
- Your own list of forbidden words. Each project can name the words an agent must not say; every hit shows who said it, in what form, with the quote — and there is an alert rule for it. The metric formerly labelled “Stop words” is now called Agent uncertainty, which is what it always measured: hedging about price, deadlines and promises.
- Every analysis is independently checked before it reaches you. Statements about safety, agreements and CRM fields must be backed by the transcript; anything that cannot be is withheld and the record is marked for review, and CRM automation acts only on a verified analysis. Organizations that want a human in the loop can ask us to enable the Review Queue (beta), where withheld actions are approved or rejected. Re-analysis no longer overwrites the previous version, so history is kept.
- Metrics stopped grading what they cannot measure. CRM completeness stays silent when there is no CRM to compare against; qualification no longer expects a private buyer to name a budget and a decision-maker; a promising sale is no longer an “attention” reason next to threats and data leaks; and voice metrics — pitch variability, speaking ratio, pauses — are real measurements again, kept on re-analysis. A zero result is shown as zero, not hidden.
- Free plan: 100 analyzed minutes a month instead of 30 — for every free organization at once, no action needed.
- Data retention is yours to set — from 1 to 365 days. Shorten the window and Aelo shows how many records that would remove before it changes anything.
- Notification settings in one place. Rules, recipients and channels are now one section, in the order they apply, with a summary of what you actually receive today; digests can be switched off for the whole organization. Save works the same way on every settings screen — bottom left — and leaving with unsaved edits asks first, including when you switch organization.
- Privacy in alerts. Telegram alerts — team channels and personal ones alike — no longer include the other party’s name, number or quotes: only the rule, the severity, the category and a link to Aelo. Where a contact is still shown, in the app, in e-mail and in webhooks, it is masked to a first name and a surname initial, or to the last digits of the number. Marketing e-mail is sent only to people who separately opted in.
- CRM connections you can switch off — and back on. Disconnecting a Bitrix24 or Uspacy installation now really stops the flow, and a Reconnect button brings it back without reinstalling. Signing in from Bitrix24 no longer needs an e-mail address: you are recognized by your CRM identity.
- The Analysis Setup hub explains each step — what it decides, what happens if you skip it, and where the result shows up — and no longer scrolls the editor out of view. Renamed for clarity: “Script” is now Script rules, “prompt profile” is analysis profile. The “Competitions” page has been removed, and the team quality table lists people without ranks or medals.
- Smaller fixes you may notice: the projects list filters correctly and “All” includes paused projects; the quality figure on project cards is a 30-day window; “Open in CRM” leads to the record’s own portal; call statistics respect the selected project; a dashboard alert link opens that alert; counts and rule-builder labels read naturally in every language.
Compliance settings that fit your jurisdiction, and Aelo speaks your language from the first screen · 2.26
- Set up recording compliance the way your organization actually works. The approach and the legal basis are no longer limited to consent and to GDPR article numbers: if your organization does not rely on the consent of call participants, choose Other lawful basis and then select the basis that applies — including Other basis under applicable law for one defined outside the listed categories. Every option now explains in a line what it means in practice.
- The compliance screen is available in your language. A language switcher sits on the screen itself, so the declaration you sign is one you can read. Nothing is preselected for you either — the approach, the jurisdiction and the legal basis are yours to state, and the form waits until you have.
- Installing from Bitrix24 sets up Aelo in your portal’s language. The organization, its project and the sample data on the first dashboard now all follow the language of the portal you installed from, instead of starting in English and waiting to be corrected by hand.
- Times and durations read naturally in all four languages. Minutes, hours and seconds are now written the way each language writes them — “1 хв”, “8 год 30 хв”, “hace 5 min” — across dashboards, widgets and record cards.
- Dashboard filters accept more than one project now. Select two or more and every number reflects exactly that set — previously only the first project you picked was applied, silently narrowing the results to one.
- The selection carries through when you drill into the records list, so the records you land on match the projects you just filtered by, not just one of them.
- Archived projects no longer show up in the project filter. Only active and paused projects are listed, so closed-out projects don’t clutter the dropdown.
- A paused project stops accepting new records everywhere — CRM sync, the public API, and file upload now all decline new calls and chats for a paused project, the same way an archived project already did. Records already in the project are unaffected.
- The printed report now carries every section of the analysis panel. Agreements reached, voice metrics, script adherence, business intelligence, the analysis profile and the deal’s stage all travel with the document — so a report forwarded to a manager or handed to a client shows the same picture you see on screen, not a shorter one.
- It reads as a document, not a screenshot. The report is laid out in Aelo’s own paper design, the one this site and our emails use, so it prints cleanly and looks like something worth attaching to an email.
- Headings and metric names are in your language, in all four we support.
- A check that did not run says so. “Passed”, “failed” and “not applicable” are now three different answers instead of two, so a blank line no longer has to be guessed at.
- A new organization no longer starts analysing on its own. Calls flow in and appear in the list from the first minute, so you can see the integration is working, but nothing is transcribed and no minutes are spent until you press Start analysis. You get the time to set up projects, criteria and prompts first.
- What arrived while you were setting up is offered separately, with the price shown up front — how many conversations, how many minutes, and how much of it goes beyond your plan. You decide whether to process all of it or only today’s.
- An empty balance now reads as “top up”, not as an error. Conversations wait in an “Awaiting top-up” state and resume once the balance is topped up, instead of appearing as failed.
- Compliance is confirmed right after installation, before the setup questions — so calls stop being turned away during those first minutes.
- Aelo now works inside Uspacy. Install it from the Uspacy Marketplace and your calls flow into Aelo the same way they do from Bitrix24 — analysed, scored and delivered back to the CRM card. Bitrix24 is no longer the only way in.
- Importing your department tree keeps every employee, not only the ones already using Aelo. People without an account are listed as pending and become full members automatically once they sign in — you no longer have to re-import after onboarding your team.
- Large org charts stay workable. Filter by name, collapse branches, or switch to a “problems only” view to see just the departments that need attention.
- Set your compliance settings without leaving the CRM. The organization owner chooses consent mode, jurisdiction and legal basis right inside the embedded app.
- Import your company’s department tree from Bitrix24 under Settings → Team → Org Structure. Aelo matches employees to their Aelo accounts by email address and shows you by name anyone it could not match.
- A department head sees the calls of everyone below them in the tree — their own department and every department under it — without needing a project assignment. This works alongside project supervision, not instead of it: whoever oversees a project keeps seeing that project.
- Assign a head by hand for any department, including ones where Bitrix24 names nobody. A manual assignment takes precedence over the portal and survives later imports; when the portal names someone else, the row says so.
- The same boundary applies everywhere — the call list, the record card, transcripts, analyses and search all agree on what a person may open.
- Projects are staffed from either side. Assign projects to a person under Settings → Team, or open a project’s own Team tab and choose who supervises it. Inviting a supervisor now asks which projects they will oversee, and the team list shows at a glance who is waiting for an assignment.
- A supervisor sees the calls in the projects they oversee — transcripts, recordings and analyses — and the alerts and daily digest cover the same projects, so what they are told matches what they are responsible for. (Since 2.19 a supervisor can also see calls through the department tree — see above.)
- Agents reach their own calls directly, without needing a project assignment, and only their own.
- Rating an analysis is open to everyone who can see it, agents included — the quickest way to tell us where the AI read a conversation wrong.
- Alert rules can require a specific phrase and report which mandatory phrases a conversation missed, so a script commitment becomes something you can measure.
- Alerts reach your team chat, with sensible per-role defaults out of the box and one-click Telegram — no setup needed before the first alert arrives.
- A rule tells you on its card when its metric is no longer available, so a rule that has stopped matching is visible instead of quiet.
- The support chat knows who it is talking to inside the Bitrix24 app, so you can ask a question without introducing yourself first.
- Call direction is read from the call’s own numbers. Phone systems vary in how reliably they state direction, so Aelo determines it from the record itself — which keeps the client’s number and the agent’s on the right side of every call.
- An inbound call says which line it came in on, so you can see which of your numbers the customer dialled.
- The customer’s number is always on the card, even when no contact name is known — on an inbound call it is the one fact that identifies the caller.
- A number where there is no name. Some phone systems do not attach an operator to a call at all. Aelo shows the extension that handled it, so calls from different seats are told apart even when no names are available. This is separate from the line: that is the public number the call went through, this is the seat that answered it.
- Every priority alert carries the line that triggered it. The card shows the quote from the conversation and where it was said, with the most serious alerts first — an older critical one stays above a newer minor one. You can tell at a glance whether a card deserves your morning, instead of opening five records to find out.
- Opening a record from an alert plays the relevant moment. Instead of starting at the beginning, playback jumps to a twenty-second window around the quote, with one control to keep listening to the rest. It works the same inside Bitrix24.
- Two actions moved into the alert itself. When someone promised to call a client back, the alert can create a Bitrix24 task or a planned call without leaving the page — and repeating the request will not create a second one. When a client’s tone dropped during a conversation, the alert can schedule a coaching session for that agent, tied to that recording.
- Aelo can check whether promised callbacks were actually logged. If a conversation contains a commitment to call back and there is no matching open call in the CRM, you get an alert. This is off until you switch it on for a project — turning it on also enables extracting agreements from conversations, and the app says so before you confirm.
- Client accounts see the same team picture as supervisors. Team overview, quality trends, calls to review and coaching now live on the client dashboard too, computed from the same data rather than a parallel version of it.
- Recordings show which line the call came in on, for telephony that distinguishes several numbers.
- Billing follows the conversation. The balance check and the charge are based on how much was actually spoken.
- For conversations processed through the new write paths, phone numbers, emails, payment cards and valid IBANs are removed from a transcript on write. For those paths, only the redacted text is kept; this was not retroactive and original audio remains unchanged. What gets removed is confirmed rather than guessed: card numbers by their checksum, IBANs by their country’s format, phone numbers by whether the number exists in a real numbering plan. Business figures stay intact — a sum, a date, an order number is not a phone number.
- A new page explains exactly what happens to your data. Personal Data in Transcripts lists what is removed, what is kept, and — just as plainly — what the redaction cannot catch: your call recordings are stored unchanged, records created before this release are not rewritten, and a number dictated in words is not detectable.
- CRM auto-fill note. Fields whose value is itself a phone number or an email can no longer be filled from what was said in the call. The contact’s own number is unaffected — it comes from the record, not from the transcript.
- Canceling or downgrading now asks why, and confirms the change. When you start a cancellation, Aelo asks what prompted it and offers a fitting option before anything takes effect; downgrading a plan asks you to confirm first, so neither happens on an accidental click.
- Connecting a data source is easier to navigate. Integrations are grouped by type — telephony and CRM — in a clean two-column layout, so the one you need is easier to spot as the list grows.
- The business overview shows what you have left. A new card puts your remaining balance and included minutes alongside the existing metrics.
- Your Bitrix24 portal language carries into Aelo. The interface language set in the portal now follows through to the app and your project.
- What separates the plans is included minutes, the per-minute rate beyond those minutes, and access to the public API. Everything else — Bitrix24 and smart process, CRM import, routing rules, annotations and reviews, direct telephony, email digests — is part of every plan, Free included.
- Changing plan shows what you will be charged. The confirmation names the amount that comes off your card at that moment, calculated from the same proration as the charge itself.
- Your balance is always visible — including on plans where we credit the account under an agreement rather than you topping it up by card.
- Emails from Aelo keep their layout in every major mail client, Outlook included.
- The public API now appears where you connect your calls. Adding a data source shows it as a fourth option alongside Bitrix24 and the telephony providers, and takes you to Settings → API Keys, where the plan requirement is explained in place. That section is visible on every plan now — including Free — so you can see what the API does before deciding to upgrade.
- Plan cards read the same source that bills you. Each plan shows its price, included minutes and the rate beyond them, and — for paid plans — what becomes available for the first time at that level, so the card cannot drift from your invoice.
- Unitalk joins the source settings, and Ringostat is listed with the cloud PBX providers rather than call analytics.
- The data-sources guide covers connecting via the API, in all four languages.
- A public upload API. You can now send calls and chats into Aelo straight from your own code — no Bitrix24 app required. Create a secret key under Settings → API Keys, then post recordings to the API and they flow into the same analysis pipeline as everything else. Available on Starter and above.
- Built for integrations. Each key is scoped to what it may do, requests are rate-limited and idempotent, and the API tells you up front — before anything is stored — when a record can’t be processed on your current balance. Full details are in the API reference and upload guide.
- Installing from Bitrix24 takes seconds. Demo data is written in bulk, so you land in a ready dashboard almost immediately.
- Every capability is on from day one. Alert rules, call scripts and data export are now included on every plan, and upcoming features appear as previews you can explore — no hidden switches to hunt for.
- The app speaks your portal’s language. Installing from Bitrix24 picks up the language of your portal profile everywhere: the interface, organization emails and the default analysis language of your project.
- A supervisor view for owners. The dashboard gains Quality and Agents tabs, so owners get the same per-agent quality breakdown supervisors use.
- Progress at a glance. The agent dashboard shows the score trend as daily bars, and agent names in “Needs Attention” and “Top Improvers” now link straight to that agent’s dashboard.
- Budget got its own tab in Plan & Billing, so spending controls no longer hide behind the plan details.
- A guided “Analysis Setup” hub. Everything that shapes how calls are analyzed — evaluation criteria, scripts, category assignment, project overrides and delivery to the CRM — now lives in one place, laid out as a pipeline with a live readiness status on every step. The new “Configuration” section in the sidebar takes you straight there.
- One records list instead of two. The “Analyses” page merged into “Records”: analysis quality and sentiment are now columns in the records table, with filters to match (including a QA-score range) and column visibility that remembers your choice. Old links redirect automatically.
- A tidier records list. In the narrow layout the deal outcome shows as a colored dot with a tooltip, long call series group sensibly in the depth funnel (1–5, 6–10, 11–50, 51+), and short-call detection respects each project’s own threshold.
- Analysis runs on our AI provider’s newer recommended interface, which measured as more reliable end to end. Your transcripts are still not retained by the provider.
- Calls that move a customer’s deal count as business calls. A bank calling about a customer’s loan, a leasing company or a partner advancing a specific deal are categorized and scored as business calls. Personal and internal calls go to “Other”, as they should.
- Categorization retries before it gives up. If it still cannot decide, the call is left uncategorized rather than given a category that does not fit.
- Trends and Conversion in your language. The client dashboard’s newest tabs are fully localized in Ukrainian, Russian and Spanish, and project delivery settings show which CRM fields are already loaded.
- Speaking pace measured against the transcript. Pace is counted from the words actually said rather than estimated from the audio signal alone, so the words-per-minute figure and its slow/normal/fast verdict describe the conversation. When the measurement cannot be made reliably, Aelo says so instead of showing a confident number.
- Polish across the interface. Empty states name the next step, speaker colours follow the speaker’s role, and Ukrainian, Russian and Spanish wording is more consistent throughout.
- Different scripts for different calls. Bind a script to a call category and pin the analysis config a project uses, so a support call is no longer graded against a sales script.
- A fairer quality score. The score now averages six skills instead of seven. CRM completeness left the rating: it applies to a minority of calls, so averaging it in penalized agents for data collection that was never their job on that call. It stays as its own compliance indicator. Expect scores to shift slightly upward for teams that were carrying that penalty.
- CRM completeness knows when it does not apply. If the customer is already in your CRM — a linked deal, contact or company — the metric reports “not applicable” and drops out of the rating, instead of scoring low for a task the call never had.
- Scorecards that follow the deal stage (beta). Aelo can read a deal’s stage from Bitrix24 and grade the call against the scorecard bound to that stage, so a first call on a fresh lead and a contract-signing call are no longer judged by the same criteria. Opt-in per organization — ask us to switch it on.
- Deal outcomes on the call. Calls now carry the outcome of the deal they belong to and how that deal moved between stages, with a conversion funnel on the Conversion tab.
- Dashboards that explain their numbers. Quality trends mark the day you changed the AI configuration, KPI tooltips say where each number comes from, and supervisors get “objections the team drops”, “skipped script steps”, and a real compliance pass rate.
- A coaching plan that writes itself. Each agent’s plan is built from the improvements their own calls suggested.
- How it sounded, not just what was said. The analysis panel now shows pace, pauses and loudness measured from the call audio.
- Every quote comes from the transcript, checked against it word for word, and categorization moved to a newer model picked by a head-to-head evaluation.
- Tell the AI about your business. Organizations and projects can describe what they do and what they want out of analysis; that context goes into every call we analyze.
- Recover calls that lost their recording. Admins can spot calls whose audio never arrived and re-fetch it from the CRM in batches.
- Real trends on every metric. Every KPI on every role dashboard shows its change against the previous period, including per-agent trends in the leaderboard.
- Conversion funnel for call series. The owner dashboard shows how call series progress stage by stage, filterable by project, plus a breakdown of calls by direction, project, and hour of day.
- Call category mix everywhere. Every dashboard now includes a breakdown of analyzed calls by category — for the whole team, per organization, and personally for each agent.
- A real toolkit for supervisors. Hourly load and per-agent workload charts, a “calls to review” queue that surfaces flagged or low-scoring calls with one-click drill-down, script adherence by agent, and a working coaching tab.
- Agent growth view. Agents can jump straight from a weak focus area to the exact calls that lowered it, and track their weekly streak and personal bests across their full history.
- Owner finances at a glance. A revenue chart, cost breakdown by type, and balance with estimated runway — all computed from your actual usage charges.
- Operations for admins. Integration health at a glance, processing errors grouped by source, and one-click retry right from the errors list.
- Clear empty states. When a period simply has no data, dashboards say so in words.
- Dashboards speak your language. Relative times, chart labels, categories, and coaching insights are now fully localized in all interface languages.
- More accurate call categorization. Internal and personal conversations are told apart from customer ones, and a call that mixes small talk with a real business request — prices, availability, an order — is routed to the customer category it belongs to.
- “Other” is a described call, not a scored one. Personal and internal calls get a summary, topic, sentiment and key moments, and the analysis card explains why a sales score would mean nothing for them.
- Call category at a glance. The record card header now shows the call’s category tag — the same one as in the records list — so you always know what kind of call you’re looking at without going back to the list.
- Smarter re-analysis. Re-running an analysis now defaults to “Auto — category profile”: Aelo picks the evaluation profile bound to the call’s category, exactly like the normal pipeline. Selecting a specific profile remains available as an explicit override when you want particular criteria.
- Speaker-level flags rest on evidence. Profanity and attention flags name a speaker only when the transcript shows it, and critical moments — churn risk, competitor mentions, sharp sentiment drops — are flagged more reliably.
- Guided start inside Bitrix24. New embedded users get a welcome narrative with sample data for their industry, and a “Full portal” button opens the complete Aelo workspace in one click — no separate sign-in.
- Category filters on the analysis card make it easier to jump to the score, script, speech, or insights sections.
- Fuller owner dashboard. Organization owners now see the complete administrative picture — team leaderboard, sources, alerts, and delivery management included.
- Smarter follow-up routing. Commitments that Aelo detects in a call now turn into the right Bitrix24 action automatically — an open promise becomes a record comment, while a “call you back” becomes a scheduled call activity. Each one carries a concrete due date and links back to the parent deal.
- Call-chain tracking. Calls tied to the same CRM entity are grouped into a series, with each call numbered in sequence — so you can see how a deal progressed conversation by conversation.
- Analytics into Smart Processes. Every analyzed call writes its full metric set (quality score, sale probability, sentiment, component scores, and more) into a dedicated Bitrix24 Smart Process item, kept up to date automatically.
- Auto-fill empty fields. Delivery can populate blank CRM fields from the analysis without overwriting values your team already entered.
- Demo analyses are clearly marked. Analyses generated from sample data now show an explicit notice, with a nudge to connect a real source.
- Clearer short and missed calls. Very short calls (under the ingest minimum) and missed calls are now labelled everywhere, so it’s obvious why they don’t carry a quality score.
- Transparent prepaid billing. Aelo moved to a prepaid model with live Stripe payments and minutes-based pricing. Top up your balance, see what each analysis costs, and track spend from the dashboard.
- EU AI Act and GDPR documentation pass. A full review of how data is handled, with refreshed Privacy Policy, Terms, DPA, and sub-processor documentation.
- Redesigned website and pricing, plus a platform-wide pass on usability, accessibility, and translations.
- Category-bound prompt profiles. Analysis now adapts to the type of conversation (sales, support, and more), so each call is evaluated against the criteria that actually matter for it.
- New telephony connectors: Unitalk, Binotel, and StreamTelcom join the supported integrations.
- Email digest reports — recurring summaries delivered straight to your inbox.
- Faster, more reliable transcription with an upgraded speech-to-text pipeline.
- Bulk-resolve for alerts — clear all matching alerts in one action, with an accurate live count shown in the sidebar.
- The platform is now Aelo (rebranded from AICA), with a refreshed design system across the app and website.
- Demo Data v2 — explore the full product with realistic sample calls before connecting your own.
- Public documentation site — the guides you’re reading now.
- Component-level scores in the Analyses grid — drill into the individual criteria behind each conversation’s overall score.
- Agent rating & feedback — rate analyses and leave coaching comments, with a dedicated stars column in the records view.
- Filter bars on Analyses and Alerts, plus a faster, smoother dashboard.
- Stripe billing for subscriptions and usage.
- Semantic search across your conversations — find calls by meaning, not just keywords.
- In-app product tours that walk new users through each area.
- Consent gate to support compliant recording.
- Embedded Bitrix24 app — run Aelo directly inside your CRM, with controls over how results are delivered back to deals.
- Guided onboarding and demo data for a faster first-run experience.
- GDPR groundwork across data handling and consent.
- Aelo reaches 1.0: a redesigned interface, public website, documentation, and feature flags for controlled rollouts.
- Category-aware analysis and lower AI costs.
The early releases established the core platform:
- AI Script Parser — turn your sales script into automatic adherence checks.
- Call categorization powered by multiple AI providers.
- Embedded mode and a rebuilt, role-based permissions model.
- Multi-language interface with full localization.
- A major performance and UX overhaul of the analytics experience.
Looking for the technical, version-by-version history? That lives in the project’s internal changelog. This page is the curated, customer-facing view.