Skip to content

Strict Referenced After Agent

Strict-Referenced-After Medical AI Assistant. This endpoint provides an answer-first-then-verify agent that: This is the opposite approach from /strict-referenced which searches first then answers. This agent answers first, then verifies and potentially revises based on research.

  • Try it: /agents
  • API Endpoint: /agent/strict-referenced-after
  • FastAPI Docs: /api-docs

Key Features

  • First provides an initial answer based on AI knowledge
  • Then searches for references to validate or invalidate the initial answer
  • Revises the answer if research contradicts the initial response
  • Always provides well-referenced final answers

System Prompt

System prompt not found in agent source code.

User Prompt Template

AGENT_USER_PROMPT_TEMPLATE

Profile: {profile}

Messages:
{messages}

API Reference

Endpoint: POST /agent/strict-referenced-after

Interactive Docs: FastAPI Swagger UI

Example Usage

curl -X POST http://localhost:8000/agent/strict-referenced-after \
  -H 'Content-Type: application/json' \
  -d '{
    "messages": [{"role": "user", "content": "What are the symptoms of diabetes?"}],
    "profile": "Patient with family history of diabetes"
  }'