Matt Pocock shares a prompt for having AI agents evaluate new tech via draft PRs
mattpocockuk · x · 2026-11-17
TypeScript figure Matt Pocock shared a "prompt of the day" for using AI coding agents to evaluate whether a new technology (example: XState v6 beta) is worth adopting.
The workflow has the agent: research what the tech does, find the gnarliest problem in your codebase it could help with, build a proof-of-concept in a draft PR, fully verify the results, then grade it on six dimensions:
- API nuance (more choices are worse for agents)
- Type safety
- Testability
- Cyclomatic complexity introduced
- Docs quality
- Deployment changes needed
The agent then gives an overall recommendation. He invites readers to drop in any technology they're curious about.
More from coding & agent
- Pageloop Launches a Docs Agent That Auto-Captures Screenshots and Updates Stale Docs — prasanna_says · 2026-11-17
- OutfitterBench tests LLM agents on 200-day rental business, exposing commitment failures — Jie Huang · 2026-11-17
- Craftax framework evolves code policies via feedback cascade, reaching final stage 50% of time — Víctor Gallego · 2026-11-17
- Entity disambiguation: sentence context hits 97.9% vs 63.5% for name matching — YvesMulkers · 2026-11-17
- XState v6 Beta Launches: State Machines Rewritten for the AI Agent Era — mattpocockuk · 2026-11-17
- Motion launches Claude Code for Video Editing: raw footage plus one prompt, auto-edited — CurieuxExplorer · 2026-11-17