Domain
Events
Selected work / Almaty Marathon
Almaty Marathon
An event support agent built for live participant questions, changing policies, and clean handoff to people when needed.
Region
Central Asia
Use case
Participant support
Almaty Marathon
Support agent, event rules ingestion, policy updates, QR and pack-pickup flows, escalation logic.
The work
The agent answers questions about registration, rules, schedules, refunds, transfers, and pack pickup while routing complex cases to human support.
What mattered
Event support changes quickly. The system needed clean knowledge updates, reliable boundaries, and escalation for questions where automation is the wrong call.
What shipped
We built the support agent, event rules ingestion, policy update flow, QR and pack-pickup scenarios, and escalation logic.
Case study
Almaty Marathon
An AI agent that runs the first line of support for one of the largest running events in Central Asia. Participants write into WhatsApp and Instagram with the same questions every day — when does it start, what are the rules, how do I pay, where do I pick up the pack — and the team behind the marathon could not keep up. The agent answers nine out of ten of those messages on its own. The tenth one — a refund request, a complaint, a VIP, a sensitive case — gets picked up by a human with a clean summary already in their inbox.
Problem
A call centre that could not keep up with the room.
A marathon at this scale pulls thousands of participants writing in at the same time across several channels. The call centre never had a chance to be fast on the easy stuff, which meant the difficult cases — complaints, refunds, conflicts — landed on already overloaded operators. The goal was not to replace the team. It was to take the predictable ninety percent off them so the remaining ten could be handled properly.
Solution
Automate the first line. Hand off the cases that need a human.
The agent picks up every message across WhatsApp Business API and Instagram (via Meta Business Suite) and answers from the marathon's knowledge base — rules, schedule, registration, payment, documents. A second layer watches for cases that need a person: complaints, threats, VIPs, refunds, withdrawals, anything that looks unusual. When one shows up, the agent stops, summarises the conversation, attaches the reason, and pings the responsible manager on Telegram or WhatsApp. The human walks in with context, not from zero.
Technical work
Multi-channel agent with strict escalation rules.
The agent runs on Python with Google ADK as the multi-agent layer — agent logic, conversation scenarios, routing of complex cases, prompt architecture all live there. The knowledge base is the marathon's FAQ, rules and registration policies. On the quality side we treat support like a moving target: we collect reference conversations, build datasets from the best operator replies, and run an AI Judge that scores the agent's answer against the reference. The point is not "AI sounds smart" — it is "AI sounds like the team that already does this well".
Related work
Magnum HR Agent
An AI HR agent for a Kazakhstani retail chain: candidate screening, internal knowledge, vacancy fit, and recruiter workflows.
- Built
- Conversational agent, admin panel, knowledge ingestion, eligibility logic, age logic, notification flows.
- Stack
- Internal HR systems · Infobip · WhatsApp · Multilingual LLM
Olzhas — Magnum Knowledge Base
An internal AI assistant for Magnum employees: ask a question in plain language, get an answer pulled from the company knowledge base.
- Built
- Conversational assistant, RAG pipeline over internal knowledge, admin panel for the operations team, onboarding flows.
- Stack
- Python backend · RAG · Multilingual LLM · Admin panel
Compass
A supplier onboarding workflow for Compass, focused on moving operational steps out of scattered manual coordination.
- Built
- Structured onboarding flow, internal workflow logic, status handling, and operator-facing product surfaces.
- Stack
- Workflow product · Internal tools · Operations
Running an event or a service where the same questions arrive in waves?
We help operations teams put a real agent on the first line: WhatsApp, Instagram and Telegram on one backend, with escalation that hands the hard cases to a human together with context.