Skip to content
Get in touch
A scroll of five illustrated principles points to a robot reviewing its work with a magnifying glass. A curved arrow moves from a rejected pink draft to an accepted green draft.
Reviewed visual · version 1

RS Glossary

Constitutional AI

Constitutional AI is an approach in which an AI system is trained or guided using an explicit set of written principles to critique and revise behavior, often alongside model-generated feedback.

Review state
Reviewed in POC
Freshness
Current
Version
2
  • Constitutional AI

Remember it this wayWritten principles help guide critique and revision.

In plain language

Instead of relying only on individual human ratings for every example, developers state principles that the system uses during parts of training or response revision.

Why it matters

Making principles explicit can improve consistency and inspectability, but the choice, interpretation, priority, and cultural context of those principles remain governance decisions.

Example

During training, a model evaluates draft answers against a written set of safety and helpfulness principles and revises responses that conflict with them.

Common misconception

A constitution does not make a model legally governed, universally aligned, or free of human judgment. People still choose the principles and training process.

Related terms

Sources

Learn more

  • Examine principle choice through [[policy-leakage|Policy Leakage]] and the broader objective through [[alignment|Alignment]].

Public history

45 recorded events · 45 public summaries

  1. A potential shared concept was discussed and selected for initial glossary drafting.

  2. The captured candidate received a complete initial draft and entered section-level human review.

  3. Radar reviewed the initial definition draft for human consideration.

  4. Radar reviewed the initial plain-language-explanation draft for human consideration.

  5. Radar reviewed the initial why-it-matters draft for human consideration.

  6. Radar reviewed the initial example draft for human consideration.

  7. Radar reviewed the initial common-misconception draft for human consideration.

  8. Radar reviewed the initial remember-it-this-way draft for human consideration.

  9. Radar reviewed the initial related-terms draft for human consideration.

  10. Radar reviewed the initial sources draft for human consideration.

  11. Radar reviewed the initial learn-more draft for human consideration.

  12. A proposal was opened for section-level human review while preserving the current version.

  13. A human reviewer opened a proposed revision while preserving the current approved or captured version.

  14. definition approved by a human reviewer.

  15. plain-language-explanation approved by a human reviewer.

  16. why-it-matters approved by a human reviewer.

  17. example approved by a human reviewer.

  18. common-misconception approved by a human reviewer.

  19. remember-it-this-way approved by a human reviewer.

  20. related-terms approved by a human reviewer.

  21. sources returned for revision.

  22. learn-more approved by a human reviewer.

  23. Requested wording was prepared without changing approved or existing sections.

  24. Radar reviewed the pending sources section for human consideration.

  25. Radar must rereview the complete constitutional-ai term after an accepted text change.

  26. Radar must rereview the complete constitutional-ai term after an accepted text change.

  27. Radar must rereview the complete constitutional-ai term after an accepted text change.

  28. Radar must rereview the complete constitutional-ai term after an accepted text change.

  29. Radar must rereview the complete constitutional-ai term after an accepted text change.

  30. Radar must rereview the complete constitutional-ai term after an accepted text change.

  31. Radar must rereview the complete constitutional-ai term after an accepted text change.

  32. Radar must rereview the complete constitutional-ai term after an accepted text change.

  33. Radar must rereview the complete constitutional-ai term after an accepted text change.

  34. sources approved by a human reviewer.

  35. sources approved wording became the current section text.

  36. All section gates are approved; content version 2 is now a fully approved term.

  37. Radar rereviewed the human-approved definition wording for this exact version.

  38. Radar rereviewed the human-approved plain-language-explanation wording for this exact version.

  39. Radar rereviewed the human-approved why-it-matters wording for this exact version.

  40. Radar rereviewed the human-approved example wording for this exact version.

  41. Radar rereviewed the human-approved common-misconception wording for this exact version.

  42. Radar rereviewed the human-approved remember-it-this-way wording for this exact version.

  43. Radar rereviewed the human-approved related-terms wording for this exact version.

  44. Radar rereviewed the human-approved sources wording for this exact version.

  45. Radar rereviewed the human-approved learn-more wording for this exact version.

Source: vault/Glossary/terms/constitutional-ai/term.md · sha256:148f01b32518e46deb3cadb241814ec36e8f8055ffe17232a45d341dfd14d603 · Release: rs-glossary-glossary-team-poc-0.5.5-2026-09-02