Search for a command to run...
Series
A comprehensive, code-first series on building production-grade AI systems with the Model Context Protocol (MCP) and TypeScript. From your first MCP server to multi-agent orchestration, RAG pipelines, observability, and global deployment — every post is packed with real, runnable code.
One agent cannot do everything well — build an orchestrator that decomposes tasks, spawns specialist sub-agents, runs them in parallel, and synthesises their results into a single coherent answer
When multiple AI agents share an MCP server, make every tool call, session event, and error visible in real time — broadcast them over SSE and render a live dashboard that shows exactly what your agents are doing
Stop guessing whether your RAG agent is getting better or worse — build a systematic eval framework that scores faithfulness, relevance, and precision, then gate your CI pipeline on it
When Tenant A searches your knowledge base, they must never see Tenant B's documents — enforce this at the database level, not in application code
Give your AI agent long-term memory — ingest documents, embed them into a vector database, and expose semantic search as an MCP tool so Claude can answer questions grounded in your own knowledge
From Docker image to live HTTPS endpoint — deploy on Koyeb and Railway for free, or Render and Fly.io for a few dollars a month, all wired to a GitHub Actions CD pipeline
