
Why I asked what problem an AI agent should solve first, and how metrics, monitoring and guardrails turn believable output into correct output.
I build AI, then try to break it.
Computer engineering grad. I build cool stuff and write about it here mostly for myself, and for anyone else who's into the same rabbit holes. No polish, just what I actually learn while building.
Markdown supported · ⌘↵ to post
No responses yet.