Ken Priore The writing · kenpriore.com
Section

AI

AI agents fail because they don't know what "customer" means at your company Not all AI agents carry the same legal risk Agentic AI doesn't need better models — it needs a data constitution The vibe coding guy says vibe coding is passé AI models that debate themselves are dramatically more accurate RAG isn't dead, it just got rebranded as context engineering Observational memory changes the AI governance equation Law-following AI turns legal compliance from afterthought into architecture The real satisfying bottleneck in enterprise AI isn't the model Smaller models aren't a compromise — they're a governance feature The AI employee is here, and it comes with a management platform When agents forget, who's accountable?
On the record
Follow
Check your inbox to confirm.