Blog

Notes on machine learning by Mikhail Balkhaev.

Series Commercial automations Automations that make or save money, from the foundation to production. Which ones are worth building and why, where to host them, how to deploy and which tools to use. 2 of 8 parts out Series The company AI agent Building an agent that knows a company's data and answers employees within their permissions. From concept to a running service, step by step, with code. 5 of 9 parts out
  1. Company knowledge: searching documents

    Index the company wiki, write a full-text search MCP server, and teach the agent to search documents the way a person does.

    10 min readThe company AI agent · part 5 of 9agentssearchragmcp

  2. MCP: connecting internal systems

    Move the agent's tools into separate MCP servers, write our own server for the company database, and teach the agent to connect to any server from a config.

    11 min readThe company AI agent · part 4 of 9agentsmcppractice

  3. The agent loop and tools

    Give the model tools for files and shell commands, and write the harness that turns a chat into an agent.

    8 min readThe company AI agent · part 3 of 9agentspracticeclaude

  4. Talking to a model

    Take a commercial model API and write a streaming terminal chat with history in 40 lines.

    5 min readThe company AI agent · part 2 of 9agentspracticeclaude

  5. The foundation: a server, a database and deploy on push

    Rent a VPS, set it up, write the first Bun service with Postgres and migrations, package it with Docker Compose and Caddy, and deploy it with GitHub Actions.

    13 min readCommercial automations · part 2 of 8automationdevopsdockerpostgres

  6. Concept: an agent that knows the company

    What agent we are building, why a chat bot is not enough, and what parts the system is made of.

    6 min readThe company AI agent · part 1 of 9agentsarchitecture

  7. Concept: which automations pay off

    How to find the processes where a business loses money, work out whether automating them is worth it, and what the system we build them on will look like.

    9 min readCommercial automations · part 1 of 8automationarchitecture