Retrieval-Augmented Generation (RAG): inject real documents into the prompt. The model reasons over your data instead of its training memory.
This eliminates hallucination on domain-specific questions, keeps answers current, and makes AI useful for internal knowledge no model was ever trained on.
02 Weak vs. Strong
EX 01Employment contract analysis
<contract>
[Paste the full contract text here]
</contract>
Analyze this contract. Answer ONLY from the text above — do not use general legal knowledge.
1. Non-compete: Is there one? Quote the exact clause. Then in plain English: geography, duration, industries covered.
2. IP assignment: Quote it. Does it cover inventions I create on my own time? Is there a carve-out for personal projects?
3. Notice period: What does each party give? Any difference for cause vs. without cause?
4. Unusual clauses: Anything more restrictive than standard that I should ask a lawyer about?
Format: quote the relevant text first, then plain-English interpretation. If something is NOT in the contract, write "Not specified in this contract" — never guess.
→ Why it works
Document isolated in XML. 'ONLY from the text above' prevents general legal knowledge that may not apply.
EX 02Meeting notes → action items
<meeting_notes>
[Paste raw meeting notes or transcript here]
</meeting_notes>
From these notes ONLY, extract:
1. Decisions made — each as one present-tense sentence. Only include things explicitly decided, not discussed.
2. Action items — for each: owner (exact name from notes), action (what they committed to), deadline (if mentioned), blocking dependency (if any)
3. Open questions — raised but not resolved. Who answers each?
4. Deferred topics — explicitly pushed to a future meeting.
Rules:
- If an action item has no named owner, flag it as [OWNER NOT SPECIFIED] — don't assign one
- Do not add anything not in the notes
- If notes are ambiguous about whether something was decided vs. discussed, ask me
→ Why it works
Four extraction categories prevent mixing decisions with actions.
03 Key Points
01Paste the document first, then ask — don't hope the model knows it
02'Answer ONLY from the provided documents' is the hallucination kill switch
03Ask for citations: 'quote the exact sentence supporting each claim'
04For long docs: ask for relevant sections first, then answer
05RAG is the most impactful single-technique hallucination reducer
04 Model-Specific Notes
Best model for long-document RAG — 200K context, excellent citation tracking. Use <document id='1'> tags for multi-document sessions.
05 For Your Role
Paste the thing first — email, article, contract, report. Then ask 'Based on the above...' This eliminates almost all hallucination.