Next Move Theory gives you an algorithm for every product decision
Product methodology wrapped as AI skills, but frameworks like JTBD already solve this.
Find what your AI agent gets wrong — before you have a rubric. Qualitative eval for PMs.
Grounded theory methodology for AI evals before you have rubrics.
Product managers and ML engineers evaluating AI agents
LangSmith · Arize Phoenix · Braintrust
Product methodology wrapped as AI skills, but frameworks like JTBD already solve this.
Naur's 1985 theory applied to AI agents, but it's just a prompt template.
Catches AI-breaking dbt issues like conflicting revenue metrics and YAML/SQL mismatches.
Automates Astral's security framework into an agent skill that produces HTML reports.
Claude Skill for agent evals, but LangSmith and Arize already own this.
Zettelkasten automation for Obsidian—compounds research sessions, fills gaps automatically.