The content-ops skill that refuses to draft
We built an AI marketing workflow at a hackathon. About four hours in, we almost shipped a post that would have torpedoed an open deal. The two gates we wired in next were the actual product.
Topic archive
#AI
Everything published under this topic, ordered from newest to oldest.
4 posts
The eval dataset has two readers
Half our eval rows were silently skipped by the LLM judge. The fix wasn't to migrate the notes — it was to duplicate them forward, so the team and the judge can each read in the format that works for them.
Sharing Claude Code config without breaking it
Stow your way through team-shared skills and slash commands without nuking sessions, projects, or credentials. Notes from building the sync command with the tool the sync command syncs.
What an LLM-as-judge actually saves your team
Prompt iteration in LangGraph Studio breaks the moment model non-determinism shows up. Here's the eval setup that fixes it — and the one design decision that decides whether your numbers mean anything.
