Replace all "verdict" language in the lead agent prompt with "status/summary" and add prescriptive opening-line templates so the LLM produces consistent output without a "Verdict:" prefix. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| base_agent.py | ||
| brand_agent.py | ||
| channel_best_practices_agent.py | ||
| channel_tech_specs_agent.py | ||
| lead_agent.py | ||
| legal_agent.py | ||