ai_ml_operations/chat_backend
2
0
Fork 0
Code Issues 23 Pull Requests Actions Packages Projects Releases Wiki Activity

Add AI disclaimer for health and legal topics #13

New Issue
Open
opened 2026-07-26 04:55:13 -07:00 by westfarn · 0 comments
westfarn commented 2026-07-26 04:55:13 -07:00
Owner
Copy Link
Copy Source

Summary

When a conversation topic involves someone's health or legal matters, the system should surface a clear disclaimer that responses are AI-generated and are not a substitute for professional medical or legal advice.

Motivation

Users may treat chat output as authoritative. For health and legal subjects that creates risk. We need an explicit, visible disclaimer so expectations stay clear.

Requirements

  • Detect when a topic/message relates to health (medical, mental health, symptoms, treatment, etc.) or legal matters (laws, rights, contracts, liability, etc.).
  • When detected, include disclaimer text in the response (or attach it in a consistent, visible way).
  • Disclaimer should state that content is AI-generated and is not professional medical or legal advice; users should consult a qualified professional.
  • Behavior should be reliable across related follow-ups in the same conversation (not only the first turn).

Acceptance criteria

  • Health-related prompts trigger the disclaimer
  • Legal-related prompts trigger the disclaimer
  • Non-health/non-legal prompts do not show the disclaimer
  • Disclaimer copy is clear, consistent, and reusable (config/constant, not hard-coded ad hoc in multiple places)
  • Covered by tests for detection + disclaimer attachment

Notes

Implementation approach (classifier vs keyword heuristics vs prompt-level instruction) is open — pick whatever fits existing chat_backend patterns best.

## Summary When a conversation topic involves someone's **health** or **legal** matters, the system should surface a clear disclaimer that responses are AI-generated and are not a substitute for professional medical or legal advice. ## Motivation Users may treat chat output as authoritative. For health and legal subjects that creates risk. We need an explicit, visible disclaimer so expectations stay clear. ## Requirements - Detect when a topic/message relates to health (medical, mental health, symptoms, treatment, etc.) or legal matters (laws, rights, contracts, liability, etc.). - When detected, include disclaimer text in the response (or attach it in a consistent, visible way). - Disclaimer should state that content is AI-generated and is **not** professional medical or legal advice; users should consult a qualified professional. - Behavior should be reliable across related follow-ups in the same conversation (not only the first turn). ## Acceptance criteria - [ ] Health-related prompts trigger the disclaimer - [ ] Legal-related prompts trigger the disclaimer - [ ] Non-health/non-legal prompts do not show the disclaimer - [ ] Disclaimer copy is clear, consistent, and reusable (config/constant, not hard-coded ad hoc in multiple places) - [ ] Covered by tests for detection + disclaimer attachment ## Notes Implementation approach (classifier vs keyword heuristics vs prompt-level instruction) is open — pick whatever fits existing chat_backend patterns best.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
No items
No labels
Milestone
No items
No Milestone
Projects
Clear projects
No projects
Assignees
Clear assignees
twestfall westfarn (Ryan Westfall)
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: ai_ml_operations/chat_backend#13