## Title <!-- Title: [Type]: Short description of the problem or goal --> Research Agent Guardrails ## Background <!-- Why does this change need to happen? --> Keep the agent safe in production ## Existing Behavior <!-- What code or docs are changing? Link or paste as needed --> server/api/views/assistant/sanitizer.py: https://github.com/CodeForPhilly/balancer-main/blob/develop/server/api/views/assistant/sanitizer.py [437 Build an input sanitizer](https://github.com/CodeForPhilly/balancer-main/issues/437) ## Acceptance Criteria - [] <!-- What does done look like? --> ## Approach <!-- How are you tackling this? Update as you go --> ## References <!-- Anything useful — docs, links, decisions --> OpenAI Cookbook Guardrails: https://developers.openai.com/cookbook/topic/guardrails OpenAI Developer Documentation Safety: https://developers.openai.com/api/docs/guides/safety-best-practices OpenAI Moderation API: https://developers.openai.com/api/docs/guides/moderation Open AI Privacy Filter Model: https://openai.com/index/introducing-openai-privacy-filter/ Open AI Guardrails Python Package: https://github.com/openai/openai-guardrails-python ## Risks and Rollback <!-- Anything that could go wrong, or leave blank if low risk --> ## Screenshots / Recordings <!-- Before/after visuals or console output if helpful -->
Title
Research Agent Guardrails
Background
Keep the agent safe in production
Existing Behavior
server/api/views/assistant/sanitizer.py:
https://github.com/CodeForPhilly/balancer-main/blob/develop/server/api/views/assistant/sanitizer.py
437 Build an input sanitizer
Acceptance Criteria
Approach
References
OpenAI Cookbook Guardrails:
https://developers.openai.com/cookbook/topic/guardrails
OpenAI Developer Documentation Safety:
https://developers.openai.com/api/docs/guides/safety-best-practices
OpenAI Moderation API:
https://developers.openai.com/api/docs/guides/moderation
Open AI Privacy Filter Model:
https://openai.com/index/introducing-openai-privacy-filter/
Open AI Guardrails Python Package:
https://github.com/openai/openai-guardrails-python
Risks and Rollback
Screenshots / Recordings