Direct answer
Do not put private credentials, client-confidential material, sensitive personal data, unsupported claims, stale drafts, duplicated clutter, copyrighted material without rights, or material that conflicts with the pack’s purpose into an AI knowledge pack. Exclusion rules are as important as collection rules.
Why it matters
This answer explains how messy notes, files, research and AI context become a structured, source-aware knowledge asset. The value is not more files; it is selection, boundaries, retrieval, review and reuse.
What to check
- What is source material, what is synthesis and what is final customer-facing output?
- What should be excluded for rights, privacy or quality reasons?
- How will the pack be reviewed, updated and tested?
Common mistake
Uploading everything into an AI tool and calling it a knowledge base without source roles, exclusions, versioning or retrieval tests.
Caveats
Medium caveat risk: use careful wording and recheck current, technical, platform, service-scope or public-account claims before publication. Keep the answer framed as guidance rather than a guarantee.