07 · Competency
AI as a working tool
I use AI as a tool, only where it makes sense.
2
instances of the system running daily, mine and one deployed for another person
Stack
LLM agents, Telegram bots, Python
Use
Production, analytics, documents
Position
Mechanics to the machine, decisions to me
Two instances: mine and one for another person
My instance
01My task02My agent03My knowledge base04Decision stays with me
The other person's instance
01Their task02A separate agent instance03A separate knowledge base04Decision stays with them
What I built
A personal working system on my own server: a Telegram bot as the interface, a knowledge base, agents on schedule.
Automations that run every day: inbox triage, daily digests, search across conversations, document processing, calendar.
A platform running several bots with different roles on one framework.
A second instance of the system, deployed as a separate environment for another person.
What it gives in production
- A concept and a deck come together in an evening.
- Data and documents get processed without queuing for an analyst.
- A draft spec, letter or report is ready in advance, so people spend their time on the decision.
- Producer routine (statuses, digests, reminders) moves off people and onto a schedule.
Why a producer should care
Everything above I built myself and I use it every day. When I talk about AI in production, I talk from practice: what actually speeds a team up, and where the tool just gets in the way.
AI is good precisely at the mechanical part of the work. Decisions, priorities and accountability stay with the human.
Mechanics to the machine, decisions to me.
LLM agentsTelegram botsProcess automationDocument processingFast prototypingPython
All of the above stands on one specific system that I built for myself and keep running every day.
My AI agent →