3 docs tagged with "prompts"

Canonical rules for what the ChurchWiseAI chatbot and voice agent must always and never do — derived from battle-tested prompt fragments, the HEAR protocol, and the Safety Covenant

How voice agent system prompts are built from pure functions in prompts.py — church data injection, theological lens application, HEAR protocol, and runtime context assembly

Systematically review voice call transcripts for a church — identify agent performance gaps, off-topic responses, missed tool uses, and implement improvements via prompt tuning