RAG, data quality, and professional prompt management

📄 Section 5: RAG, data quality, and professional prompt management

🎯 Learning objectives

• Understand how RAG changes what the model actually sees
• Reduce hallucinations with constraints and sources
• Handle contradictions and multiple sources with clear priority
• Use meta-prompting, compression, and structured testing

RAG from a prompting perspective

In RAG the model often sees not the entire library – only excerpts that retrieval judges to be relevant. Therefore:

• Clear questions → better matching to the right chunk.
• Remind about the big picture when needed: “summarize the document’s overarching conclusions” may require retrieval to actually pick representative parts – otherwise there’s a risk of skewed output.

Reduce hallucinations

Three classic levers:

1. Restrict to delivered documents where appropriate – and provide a fixed phrase for when an answer is missing.
2. Require source support for facts you can verify against the underlying material.
3. Request explicit uncertainty when the material is thin or ambiguous.

Remember: models generate text – they don’t “know” whether they’re correct without external grounding.

Contradictions between sources

Ask the model not to pretend if the conflict is unknown. Example:

If sources give conflicting information: describe the conflict, name which documents are involved
and do not take a position on which version applies unless I have stated it.

You can also set priority: newer policy over older, governing documents over internal memos, etc.

Meta-prompting and compression

Meta-prompting: let the model first review your instruction (“what is unclear?”), suggest a v2, or generate a system prompt from a product brief. Always review the machine’s suggestion.

Compression: remove politeness fuzz that adds no signal: “Could you please be so kind as to…” → write the task + format directly.

Output anchoring: give a filled-in template with headings for the model to complete – reduces free-form responses.

Tip: in Intric’s library you’ll find, among other things, a prompt expert you can import and iterate with.

Professional iteration and data types

• Test-driven prompting: define 3–5 typical success cases, a few ambiguous ones, and some out of scope – run after every change.
• Self-review: ask the model to rate and give feedback on a response according to criteria you care about.

Tables and exports: describe column meanings, date formats, and what empty cells mean before asking for analysis. Remove irrelevant columns – same principle as context engineering: less noise.

Intric has tools that help models with certain file types – but a clear prompt is still cheap insurance.

Summary

• RAG = retrieval of chunks, not magically reading everything.
• Hallucinations are countered with constraints, sources, and explicit uncertainty.
• Contradictions require policy and transparency.
• Meta-prompting, compression, and templates improve quality faster than just writing longer and longer prompts.

Congratulations – you’ve completed the advanced course. Keep testing in real cases and return to the modules when you introduce new teams or models.

Test your knowledge

4 questions · 100% correct to pass · Review your answers when done

Start quiz →