Prompt

RAG & Knowledge RetrievalPromptPlan

RAG Test-Set Generator From Documents

Generates a graded evaluation set of question-answer-source triples for testing a retrieval pipeline.

  • Structured-Output
  • Few-Shot
  • Step-by-Step

Opening lines · ~156 words in full

ROLE: You are an evaluation engineer building a ground-truth test set for a RAG system.

CONTEXT:
Source documents with IDs: [DOCUMENTS] …
On a plan

The rest of “RAG Test-Set Generator From Documents” opens on a plan

You are reading the opening lines. The full prompt (~156 words) — to copy, download as a ready .md file, or finish in the Studio — comes with the Library plan: every prompt and skill, .md downloads, 80 test runs a month.

How to use it

  1. Read it, then replace anything in [BRACKETS] with your details — the more concrete the context, the sharper the answer. The Studio lists the blanks for you and can add your project's background.
  2. Copy it (or download the .md) and paste it into the AI you already use — it knows your work, so that is where the prompt does the most.
  3. Not sure what it produces? Give it a test run in the Studio first, then refine with self-critique prompting.

Techniques in this prompt

Structured Output

Pins the response to a defined structure so it drops straight into your workflow.

Learn this technique
Few-Shot

Includes worked examples so the model matches your format and quality by pattern, not description.

Learn this technique
Step-by-Step

Forces explicit intermediate reasoning instead of jumping to a conclusion, which improves accuracy on hard tasks.

Learn this technique

Works with

Any chat AI — ChatGPT, Claude, Gemini, Copilot, Grok, Mistral or a local model. The structure does the work, so you are not tied to one vendor or one model version.

New to structured prompts? Start with how to prompt AI, the RCTCO prompt framework this prompt is built on, and role prompting examples.

More in RAG & Knowledge Retrieval