Write to me

Email is the best way. Write to [email protected]. I read everything, and I answer when I can.

Writing

  1. Global context for AI agents: minimal to load, fast to find An AI model does not know your business. A global context is a map of that information, split into domains. Each session loads only the domain the question needs, and saves what changed.
  2. How we built the MAAT Admin Agent for gym owners We built an agent inside the MAAT Admin Dashboard. It reads the backend API through MCP-style actions, uses Jev to plan each turn, shows widgets in the chat, and is tested with a bench and real conversations.
  3. From a gym schedule picture to classes in MAAT We combined Docling OCR, an editable Markdown table, and structured output to import gym schedules. Our sales team reduced schedule setup from about 30 minutes to five minutes, with review before saving.
  4. Building an AI Brain at MAAT We are building context that people and AI can follow. A clear hierarchy connects company knowledge to reviewed procedures, so more of the team can use it. Adding knowledge as it grows is the next challenge.
  5. How we built a context tree for our agent to resolve support tasks Support work led us from manual fixes to a tree of context files. Each index points the agent to service details, task instructions, and past investigations.
  6. Express the General State what you want and the constraints that matter. A short essay on prompting, inspired by Kierkegaard, and why guesses about the method can hide the goal.
  7. Your AI Agent Deserves Its Own Repo Keep agent knowledge in version-controlled files. Organize the context, load what each task needs, and save repeated work as reusable procedures.
  8. Lessons Learned Building a Real-World AI Agent with LangGraph A translation agent needs room for feedback. This LangGraph workflow keeps the conversation in state and moves slow glossary suggestions into a background job.
  9. Advanced Langgraph: Deep dive into open deep research An analysis of how Open Deep Research splits work across agents and carries context between steps. Includes architecture tradeoffs, limits, and practical takeaways.