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 this: It's 2 AM. A customer messages our support channel, frustrated because their recent order never arrived. They want a refund, or at minimum, an explanation. They've been emailing back and forth for three days with no resolution.
A support agent is assigned. But it's 2 AM. There's no one on call. So... does the AI just handle it?
That's the question I couldn't let go of — the one this whole series exists to answer.
