AI already reads 20% of knowledge base docs, but only 1.3% are verified
femke_plantinga · x · 2026-11-18
Slite released a free ebook, The Knowledge Framework Playbook, based on analyzing 50 customer knowledge bases, interviewing 16 teams, and surveying knowledge workers. Key findings: AI agents already do 11-20% of document reads in a typical team; the median doc is 505 days old; only 1.3% of docs are verified and trustworthy.
The playbook's framework: decide what belongs, give every doc an owner, track what's verified vs. what AI cites, and act on the data. They also tested whether smarter AI search could work around messy knowledge—it can't: one cleanup did twice as much as a smarter agent.
More from coding & agent
- Managing four Docker hosts with Komodo and GitHub in one dashboard — ruhanirabin · 2026-11-18
- Lily Ray's workflow: use ChatGPT to compile your past work into shareable links — lilyraynyc · 2026-11-18
- Drawing humanity's history with JavaScript: cave art to scientific revolution — prasenx · 2026-11-18
- One-line fix cuts training step time 40%: HSDP keeps all-gathers on NVLink — FerdinandMom · 2026-11-18
- After two years on Codex and Claude, dev says you simply can't quit — rachittshah · 2026-11-18
- Cursor teases Origin, 'a git forge for the agentic era' — himanshustwts · 2026-11-18