playbook
2 notes tagged playbook in the AI agents topic. How agents are built, tuned and run: loops, harnesses, MCP, skills and coding agents, with what broke and what we measured.
- One Claude Code Project per goal: adopting Projects across many repos
How a team with many repos should adopt Claude Code Projects: what a thread sees, where it runs, and the Do and Don't lists we set.
- UX
A two-phase UX research framework (gather data, then analyze it) covering interviews, competitor analysis, personas, journey maps and flows.