Skip to the content

An AI sales manager for Avito

A stream of enquiries across several Avito stores, managers unable to reply fast enough, and leads lost to the delay. We handed the first contact to an AI agent.

Client
A multi-store seller on Avito
Industry
Retail
Year
2026
Duration
In production
The problem

The company gets a heavy stream of enquiries on Avito across several stores at once. Managers physically cannot answer every message quickly and to the same standard, and some leads are lost to the delay.

Solution

What we did
and why we did it that way.

01

Scripted dialogue

The AI agent runs the conversation on Avito: it answers product questions and holds the thread without an operator.

02

Qualification in chat

The agent works out the request and filters out off-target enquiries before a person picks them up.

03

A target action

It moves the customer to the needed step: get a contact, place an order, or hand off to a manager. The goal is configured per business.

04

Several accounts at once

One logic serves several stores in parallel, with no drop in quality and no days off.

Result

What changed
and what we measured it with.

24/7inbound handled around the clock
Autolead qualified right in the chat
1st lineclosed without an operator
Warmmanagers take already-qualified enquiries
Stack
LLMAvitoPythonPostgreSQL
Timeline

How it went
day by day and week by week.

  1. Brief

    Script and goal

    Mapped the typical questions and the target action for each store.

  2. Build

    Agent and integration

    Built the dialogue on an LLM and connected it to the Avito accounts.

  3. Production

    Launch and tuning

    Put it on the live stream and refined the wording from real chats.

Screens

How it looks
in schematics.

These are screen schematics. We do not publish client interfaces without permission

Next

A similar problem
on your side?

Describe it in the brief. In working hours we come back with an estimate of time and cost within two hours.