Six AI agents behind one growth strategy

The AI agent began transcribing every inbound and outbound call from active-sales managers. Each call was automatically turned into text, after which the agent checked it along two lines.

The first – script adherence: did the manager go through every mandatory stage of the conversation, ask the right questions, and handle objections to standard. The second – extracting data about the client: what matters to them when choosing a provider (price, speed, reliability, level of service), what their current connection speed is, what their monthly ticket is, and whether they have any issues with their current provider.

All of this data landed automatically in the client record in Bitrix24 – structured, in the right fields. The manager ended the conversation and the record was already filled in. No manual entry, no delays, no lost details.

The AI agent gathered data on every active deal and each morning produced a report for the head of sales – with no queries to managers and no manual assembly.

The report showed conversion at every funnel stage: reaching the decision-maker → agreeing to a meeting → holding the meeting → sending the details → closing the deal and payment. For each stage it was clear how many deals moved forward, how many were stuck, and which managers had below-team-average results.

On top of that, the agent analyzed call transcripts: at which points in the conversation objections came up most often and how managers dealt with them. Managing sales stopped being based on gut feeling – now it's data that refreshes every day.

Every time a new client moved from an active-sales manager to an account manager, the AI agent began tracking the quality of that transition against a concrete checklist.

Did the account manager introduce themselves to the client personally? Did they find out what matters to the client in working with a provider – not from the record, but in a live conversation? Did they identify what could be offered as an add-on and when it would be appropriate? Did they set themselves a task with a reminder?

The agent analyzed calls and CRM activity during the first month after the hand-off. If any checklist item wasn't completed, the manager received a signal that same day, rather than finding out a month later at a standup.

The fourth agent worked with already-connected clients – the ones who've been in the base a long time and are easy to stop paying attention to.

For each client the agent checked: was there a scheduled contact this month, are the issues from past requests closed, are there signs of hidden dissatisfaction – situations where the client mentioned something in a conversation but never filed a formal request.

In parallel, the agent analyzed upsell potential: it looked at the mix of services consumed, compared it with similar clients, and highlighted who could logically be offered what – with a concrete rationale, not just a "there's potential" flag.

The fifth agent worked in the contact center. It analyzed every call and message from the support team: turned conversations into text, identified the topic of each request and the overall tone – whether the client was satisfied, neutral or irritated.

On that basis the agent did two things. First – it classified requests by problem type: no connection, low speed, a billing question, a quality complaint. This gave accurate statistics on the real reasons for requests, rather than the categories an operator picked by hand. Second – it built a list of clients with a high level of dissatisfaction: those who reached out several times with the same problem or in whose conversations the agent detected rising irritation.

Working from this list, account managers made a proactive call – without waiting for the client to call in themselves with the intent to terminate the contract.

The sixth agent worked not on the outside but on the inside – helping the operators themselves in the moment of the conversation with the client.

Drawing on internal documentation, technical procedures and the accumulated request history, the agent built a knowledge base. When an operator took a call, the agent identified the topic of the request in real time and suggested a ready answer or course of action – right in the operator's interface, while the conversation was still going.

Routine questions – equipment setup, explaining a bill, standard technical problems – the first-line operator started resolving on their own, without switching to a senior specialist. Complex cases, meanwhile, were escalated faster: the agent helped the operator recognize that a question was non-standard early in the conversation.