Matt Pocock lists 18 common mistakes developers make with coding agents
mattpocockuk · x · 2026-10-13
Well-known TypeScript educator Matt Pocock outlined 18 mistakes developers make when working with AI coding agents, spanning workflow, verification, and collaboration rhythm:
- Alignment & planning: not aligning before starting, aligning too often/too hard, not thinking enough or strategically
- Context & config: skills too long, overloaded global steering files, token-inefficient custom tooling
- Verification: lax automated checks, agent unable to verify its own work, too much human review and too little automated review
- Habits: babysitting the agent, not reviewing previous coding sessions with an agent, effort level too high, not vibe coding enough prototypes
- Codebase: hard-to-navigate codebase, architecture that allows bad tests, no shared language with the agent
His overall stance: push trust and verification toward automation, give agents self-checking ability, and let humans operate at the strategy level.
Related event: Matt Pocock Lists Common Mistakes When Using AI Coding Agents(2 posts)→
More from coding & agent
- Stack Overflow Expands Stack Internal to Give AI Agents 'Trusted' Enterprise Knowledge — pchandrasekar · 2026-10-13
- Grok Bot's new X access, email and Opus turn personas into always-on agents, says creator Peter Yang — petergyang · 2026-10-13
- jscpd adds semantic cross-language clone detection to map AI code migrations — Affectionate-Blood92 · 2026-10-13
- Benchmarking Microsoft's MXC sandbox: git jumps from 10ms to 1.24s without a writable temp dir — lemire · 2026-10-13
- Let your coding agent auto-clean git worktrees and branches after deploy — NielsRogge · 2026-10-13
- Generative art built with Opus 5.5 writing Three.js code — techartist_ · 2026-10-13