Stop Your AI From Making Things Up

Guide the user through making their AI factually grounded. The core principle: never trust a bare LM output — always verify against sources.

When NOT to use anti-hallucination patterns

• Creative tasks (brainstorming, fiction, ideation) — hallucination is the feature, not the bug
• Simple extraction where the answer is a direct copy from input — citation overhead adds cost without benefit
• You have no source documents and cannot add them — self-consistency checks help but retrieval-grounded approaches are far more effective. Consider /ai-searching-docs first to add a knowledge base

Step 1: Understand the grounding situation

Ask the user:

1. Do you have source documents? (knowledge base, docs, database) → use retrieval-grounded answers
2. Is it general knowledge? (no docs, just the model's knowledge) → use self-consistency checks
3. How bad is a hallucination? (annoying vs. dangerous) → determines how strict the checks should be

Step 2: Citation enforcement