Tag
I pointed the new claude-security plugin at this very site. It spawned 82 agents, proposed 10 vulnerabilities, and then argued itself out of 9 of them. The one that survived was real — and it shipped to prod the same afternoon.
An evening climbing the loop ladder in Claude Code, from a one-shot fix to an unattended cloud routine. The lessons had nothing to do with the code and everything to do with how a loop stops: unenforceable budgets, self-writing reward hacks, and why a trapped loop cannot free itself.
The Model Context Protocol, hands on
How I turned Apache Kafka into a set of tools an AI client can call — using Spring AI's MCP server, a handful of @Tool methods, and one ugly-but-necessary servlet filter.
Open Knowledge Format (OKF) is a dead-simple convention for storing durable, executable knowledge alongside your code — no database, no network, just markdown files your AI agent can read and act on.
The Model Context Protocol, hands on
Field notes from wiring Fastmail's MCP server into an AI client and pointing it at my real inbox — the search syntax worth memorising, plus the two gotchas (deferred schemas, and stage-vs-commit on calendar events) that cost me a few minutes.