Skip to main content
Microsoft Foundry

Web Fact-Checker

Description

What this agent manifest does

Paste a set of claims; get each one checked against public sources — supported, contradicted, or unverifiable, with links.

Build an agent that takes a block of factual claims — a draft paragraph, a list of assertions, a summary — and checks each one against current public information. It uses Web Search to find supporting or contradicting sources, then returns a per-claim verdict with citations, so you can see at a glance which statements stand up and which need a rewrite. Results reflect public information available at the time of the search.

This is a single-tool verify → verdict table pattern using XML-tag prompt structure. The tags structure the loop — <extract> the claims, <verify> each against sources, <report> the verdicts — keeping verification disciplined and one claim at a time. The defining design decision is making unverifiable a first-class verdict alongside supported and contradicted: when the agent can't find a credible source, it says so rather than rationalizing weak evidence into a "supported," which is the failure mode that makes fact-checkers worse than useless. Edge cases cover opinion vs. fact, claims that hinge on a date, and sources that disagree.

This pattern applies anywhere claims need grounding before they ship. Common scenarios for this pattern:

  • Pre-publication fact-checking
  • Verifying claims in a draft or summary
  • Sanity-checking research findings
  • Auditing marketing or comms copy for accuracy
  • Vetting forwarded "facts" before repeating them

The tools it uses

This manifest uses: Bing Web Search

Use this agent manifest to understand

How to build single-shot agents using xml tags prompt structure for claim-by-claim verdict table output.

License

This agent manifest is sample code subject to Azure's licensing terms for Distributable Code under the Universal License Terms for Online Services .

Disclaimer

IMPORTANT! This manifest is for educational and experimentation purposes. Resulting agents are not production ready. Review all provided resources and carefully test agent behavior in the context of your use case. Agents you create may be subject to legal and regulatory requirements, may require licenses, or may not be suitable for all industries, scenarios, or use cases. By using any manifest, you are acknowledging that resulting agents and other output are solely your responsibility, and that you will comply with all applicable laws, regulations, and relevant safety standards, terms of service, and codes of conduct. Learn more .