An AI agent read a stale wiki page and contributed to Amazon's retail outage — who audits your docs?
femke_plantinga · x · 2026-10-28
In March, Amazon's retail site had four high-severity incidents in one week; one traced to an engineer following AI advice from an outdated internal wiki. Femke Plantinga (Slite) argues agents make knowledge maintenance harder: they answer from stale pages as confidently as current ones and generate new docs faster than anyone can review them — while documentation upkeep usually falls on someone unofficially. Slite is researching how teams keep knowledge trustworthy for both people and AI.
More from coding & agent
- Matt Pocock mulls banning useState outright in his React apps to steer AI coding agents — mattpocockuk · 2026-10-28
- Developer: tickets, code, tests and PRs should all be generated by agents — intellectronica · 2026-10-28
- Simon Willison: October 2026 is the vibe-coding-games inflection point, Opus 5.5 knows fun — Simon Willison · 2026-10-28
- Avalon-M1 trains LLM agent organisations via collective-reward RL, lifting avg score 33.5% to 45.7% — RobertTLange · 2026-10-28
- Creator chains Halo and Runway via MCP connectors in GPT for a music video workflow — aziz4ai · 2026-10-28
- Dev uses Qwen in an opencode harness to root an LG TV and strip out spyware — Switchboy1 · 2026-10-28