# Check a generated brief for unsupported claims

Use case · AI agents · Planned API workflow

Canonical page: https://datasdk.ai/use-cases/check-a-generated-brief-for-unsupported-claims

Plan a verification pass before people rely on the brief.

## Who this helps

A research agent can produce persuasive but ungrounded statements.

## How to use it

1. Require a source for each factual company claim.
2. Compare each claim with its cited evidence.
3. Remove unsupported details or label them unknown.

## Illustrative example

A proposed check would reject an invented revenue figure when no source supports it.

## What to check

Source presence alone is not enough; the source must support the specific claim.

## How Data SDK fits

The full Data SDK API is coming soon. Platform and AI-agent workflows are planning examples. Confirm access, data delivery, usage, branding, and resale terms before building or selling a feature.

These are suggested workflows, not a list of built-in integrations. Use your own approved analytics, CRM, and research process where needed. Matches and fields vary. A company match does not identify a person or prove buying intent.

## Related reading

- [Hallucination](https://datasdk.ai/glossary/hallucination): A hallucination is model-generated content that is unsupported or incorrect.
- [Human review](https://datasdk.ai/glossary/human-review): Human review puts a person in the loop before a result is accepted or acted on.
- [Source attribution](https://datasdk.ai/glossary/source-attribution): Source attribution shows where a claim or data point came from.
- [Prepare an AI company research brief](https://datasdk.ai/use-cases/prepare-an-ai-company-research-brief): Plan concise briefs tied to a matched company domain.
- [Classify company fit with evidence](https://datasdk.ai/use-cases/classify-company-fit-with-evidence): Plan a reviewable explanation of how a company meets user-defined criteria.
- [Suggest questions for a discovery call](https://datasdk.ai/use-cases/suggest-questions-for-a-discovery-call): Plan questions grounded in the company's business rather than guesses about the visitor.

[Glossary](https://datasdk.ai/glossary) · [Use cases](https://datasdk.ai/use-cases) · [Comparisons](https://datasdk.ai/vs) · [For businesses](https://datasdk.ai/for-businesses) · [For builders](https://datasdk.ai/for-builders)