RAG & Knowledge Retrieval5.0 · 0 ratings

Source Attribution Coverage Reporter

Measures what fraction of an answer is source-attributable and rewrites unsupported sentences.

Self-CritiqueStructured-OutputStep-by-Step

Prompt

ROLE: You are an attribution coverage analyst for grounded generation.

CONTEXT:
Generated answer: [ANSWER]
Source passages with IDs: [SOURCES]
Minimum required attribution coverage: [THRESHOLD_PERCENT]

TASK:
1. Split the answer into sentences.
2. For each sentence, decide whether it is fully attributable to the sources, partially attributable, or unattributable, citing the supporting passage where it exists.
3. Compute attribution coverage = attributable sentences / total sentences.
4. For each unattributable sentence, either rewrite it to be source-grounded or recommend deleting it, so the final answer meets the threshold.

OUTPUT FORMAT:
Sentence ledger: | # | Sentence | Status | Source [ID] |
Coverage: X% (meets/does not meet [THRESHOLD_PERCENT]).
Revised answer: <version where every sentence is attributable>
Removed or rewritten: bullet log of changes.

CONSTRAINTS:
- Do not introduce new facts when rewriting; only ground or remove.
- A sentence with a citation that does not actually support it counts as unattributable.
- The revised answer must be coherent, not a list of fragments.

How to use this prompt

  1. 1

    Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.

  2. 2

    Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.

  3. 3

    Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.

Techniques in this prompt

Self-Critique

Has the model critique its own draft against criteria, then revise — raising quality in a single pass.

Learn this technique
Structured Output

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

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

Recommended models

claudegpt-4ogemini

Build on this prompt

Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.

Open in Studio How to prompt AI correctly

More in RAG & Knowledge Retrieval

Grounded Answer With Inline Citations

Answers a user question strictly from retrieved passages, attaching an inline citation to every factual claim.

Read prompt

Faithfulness Auditor For RAG Outputs

Audits a generated answer against its source passages and flags every unsupported or contradicted claim.

Read prompt

Query Decomposition For Multi-Hop Retrieval

Breaks a complex question into ordered atomic sub-queries optimized for a vector search retriever.

Read prompt

Hybrid Search Reranker With Justification

Reranks candidate passages by true relevance to the query and explains each ranking decision.

Read prompt