docs: write docs/policies.md (Cedar policy engine + Bedrock guardrails)
- Dominant language
- TypeScript
- Stars
- 283
- Forks
- 95
- Avg merge
- 1d 2h
- Merged PRs (30d)
- 183
Description
Policies & Guardrails (`add policy-engine`, `add policy`) is referenced in #1577's README Policies & Guardrails section but has no dedicated guide. `docs/policies/` only contains IAM JSONs, not feature docs.
Should cover: Cedar policy engines, the form-based guardrail builder, content-filter enum (`VIOLENCE | HATE | SEXUAL | MISCONDUCT | INSULTS`), prompt-attack detection, sensitive-information redaction, enforcement modes (ACTIVE/PASSIVE).
Related to #1571 (the INSULT typo bug) — wider doc would have caught it.
Out of #1577.
Contributor guide
Research direction
Start with #1577's README Policies & Guardrails section and inspect the existing IAM JSONs in docs/policies/. Write docs/policies.md covering Cedar policy engines, the form-based guardrail builder, the listed content-filter values, prompt-attack detection, sensitive-information redaction, and ACTIVE/PASSIVE enforcement. Done when the referenced feature has a dedicated guide and the INSULT spelling is correct.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- aws
- Domain
- documentation, security
- Issue type
- Documentation
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 72/100