Series · 6 of 6 published
The Practical Roadmap to Building With AI Agents
Six parts, written while building this site rather than afterwards. It starts at the difference between a chat window and an agent and ends at what an agentic system actually costs to run. Every example comes from this site: the tools it was given, the permissions it should not have had, the retrieval bugs where the model was fine and the information was not, and the checks that now catch all of it.
- 01From Chat to AgentMost people use AI like a vending machine. I used it like a senior engineer sitting next to me, and built this whole site that way without knowing Next.js. Part one of six: what actually separates a chat window from an agent, and how to start.9 min read
- 02Giving an Agent HandsAn agent that can only edit files makes you the courier between it and everything else. Tools and MCP fix that. Part two of six: what a tool actually is, what I connected, what it fixed in thirty seconds, and the permissions file I am not proud of.9 min read
- 03Giving an Agent KnowledgeThe assistant on this site answers from my actual writing. Part three of six: RAG explained without the jargon, the chunking and search settings I actually use, and three retrieval bugs where the model was fine and the information was not.9 min read
- 04Making Agents Safe Enough to ActIf your agent can use tools, what stops it doing something stupid? Part four of six: why prompt instructions are not a security control, the database rules that make bad outcomes impossible on this site, and the gaps I have not closed.8 min read
- 05Making Agents Reliable Enough to ShipGeneration gives you code. Feedback loops turn it into engineering. Part five of six: the failures on this site where a green build was exactly the wrong goal, and how a bug becomes a permanent check nobody has to remember.10 min read
- 06From One Agent to an Agentic SystemLoops, subagents, orchestration and routing, explained without the hype, plus the economics nobody mentions. Part six of six: what this site actually runs, what it deliberately does not, and why more agents is often the wrong answer.9 min read
Stay in the loop
New posts on AI systems, engineering craft, and lessons from building in production. No spam. Unsubscribe anytime.