Chain of Verification
Break factual review into a draft, independent checks and an answer revised against the evidence.
Create a verification promptExplore team workflows →
Illustrative verification workflow
Draft the announcement from the approved release notes. Extract its factual claims as separate questions about features, availability and requirements. Answer each question from the release notes without relying on the draft’s wording. Mark unsupported claims as unverified. Revise the announcement using only supported claims…
Read the full example →
Make verification a separate task
The Chain-of-Verification paper studies a process that drafts an answer, plans fact-checking questions, answers them independently and then revises the response. Independence matters because a checker can otherwise repeat the assumptions in the draft.
Use the method when factual errors matter and the claims can be checked. It adds work and may add model calls; do not apply an expensive verification loop to every trivial formatting request.
Source: Chain-of-Verification research paper
Verify a feature announcement against approved evidence
For this practical adaptation, keep the evidence source available to the checker and treat the draft as something to test.
Illustrative verification workflow
Draft the announcement from the approved release notes. Extract its factual claims as separate questions about features, availability and requirements. Answer each question from the release notes without relying on the draft’s wording. Mark unsupported claims as unverified. Revise the announcement using only supported claims and return the unresolved questions for a human reviewer.
A second answer can repeat the same mistake
Verification without adequate evidence can create another plausible error. The paper reports results on specific evaluated tasks, not a guarantee for every model or domain. Use authoritative sources and human review where consequences are significant.
Common questions
Is asking “are you sure?” enough?
It does not establish independent verification. Identify specific claims and check them against evidence that can contradict the first answer.
Sources and review
Published by Prompeteer. See the people responsible for the product and contact the team with corrections. The linked workflow artifacts describe exactly what was checked; illustrative examples are not customer results.
Reviewed September 9, 2026
Continue your workflow
Make unsupported claims easier to catch →
Use relevant sources, explicit uncertainty, verification and human review to reduce unsupported AI claims. Learn what prompts alone cannot guarantee.
Use the method the problem needs →
Choose among source grounding, examples, task decomposition, verification and structured output. Understand the evidence, cost and limits of each approach.
Decide what a good answer must pass →
Evaluate factual accuracy, task completion and format separately. Build representative cases, failure examples and human review criteria for AI workflows.
Put the workflow to work.
Create a verification promptExplore team workflows →
Source: https://prompeteer.ai/techniques/chain-of-verification