AI agent and LLM automation development
I build assistants that use your data and APIs: they search tickets, answer customers, classify requests and subscribe users to alerts.
What is included
- An agent with tools (search, subscribe, API requests)
- Conversation memory
- Model connections (OpenRouter, DeepSeek and others)
- Request classification and routing
- Knowledge base search
- Limits, logs and guards against wrong answers
Who it is for
- Projects that need a consultant in Telegram or on a site
- Support teams with a flow of typical questions
- Services where answers must rely on real data
Result
An assistant that answers from your data instead of making things up.
Examples
HotTrip
An ecosystem around flights and tours: a portal, an AI bot, a Telegram Mini App, an API and an automated channel.
Document recognition for 1C
A 1C extension: a photo, scan or PDF of an invoice fills the document in 30–60 seconds. Local AI, no internet and no cloud.
Related articles
1C invoice recognition without the cloud: UPD and TORG-12 from a photo
An invoice from a photo can become a filled 1C document in 30–60 seconds. A local AI model runs on the client's computer, so prices, tax IDs and suppliers never reach third-party servers.
Telegram · Oct 30, 2026A Telegram bot in n8n: inline buttons, menus and a Mini App button
In n8n a bot is built from a Telegram Trigger, a branch by event type and a send node. Inline button presses arrive as callback_query and need an answer. A button that opens a Mini App is easiest to send through HTTP Request, and a bot can have only one webhook.
FAQ
How do you avoid made-up answers?
The agent gets data through tools and APIs, and answers are built from it. I limit the topic and log conversations.
Tell me about your task
Describe what needs to be done, even in a couple of lines. I will reply with questions or an estimate.