This post kicks off an ongoing experiment: building an LLM-powered support agent you can actually trust, one decision at a time. Everything described here ships in the companion repo reliable-ai-support ( code as of this post: tag post-001 ), which grows as the series does. Where I mention future topics, read them as current intentions, not contracts — the whole point of building in public is that the plan bends to what actually works. The Support-Agent Problem Picture...