---
title: "Answer questions about a named person only · Agent Wranglers"
url: https://agentwranglers.se/playbook/ai-features/guardrails-and-human-review/facts-about-people-from-sources
id: AIF-68
level: Required
applies: ai-features, eu-users
region: EU
risk: law
updated: 2026-10-27
build: a2a6bdfed830
tokens: 1144
licence: "CC BY 4.0"
licence_url: https://creativecommons.org/licenses/by/4.0/
---

# Answer questions about a named person only from records you hold

For AI agents: the [site map](https://agentwranglers.se/llms.txt) lists everything here, and this page sits under [Guardrails and human review](https://agentwranglers.se/playbook/ai-features/guardrails-and-human-review.md).

By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers.md). Updated 2026-10-27.

- ID: AIF-68
- Level: Required
- Chapter: [Guardrails and human review](https://agentwranglers.se/playbook/ai-features/guardrails-and-human-review.md)
- Rule: State facts about a named person only from your own records or retrieved sources, and cite them. With no source, say the feature has no information about that person.
- Check: Eval cases ask about five named people who are in no source. Every answer says the feature has no information and states no fact about them. A unit test feeds the output check an answer that names a person missing from its sources, and the check blocks it.
- Risk: A law broken
- Applies when: The project uses AI models, or has users in the EU.
- Region: European Union (EU). The duty comes from the law there. The rule applies only when the project serves people there, and its Applies when also holds.
- How: Models make up plausible facts about people, such as a crime, a debt or a job they never held. Readers tend to take these as true. The EDPB found that a warning about made-up output does not meet the GDPR accuracy principle on its own. Find the people a question names with a lookup of your own records or a name recogniser. Pass only their retrieved records to the model, and tell it to state nothing beyond them. Then check in code that every person named in the answer appears in the cited sources. Let people report a wrong statement about themselves. Block that answer until it is fixed or erased, as [let people see and delete their data](https://agentwranglers.se/playbook/website/privacy/data-requests.md) says. Grounding in general follows [Ground answers in your own data](https://agentwranglers.se/playbook/ai-features/retrieval/cite-sources.md) and [Say so when nothing relevant was found](https://agentwranglers.se/playbook/ai-features/retrieval/no-match-answer.md).

## Examples

**Using these examples:** they show one way to follow this rule. Keep the behaviour and the check, not the syntax. Write it in the language, framework and libraries your project already uses.

### JavaScript example

```js
export function unsourcedPeople(answerPeople, sources) {
  const sourced = new Set(sources.flatMap(source => source.people));
  return answerPeople.filter(person => !sourced.has(person));
}

if (unsourcedPeople(findPeople(answer.text), answer.sources).length > 0) return SAFE_REPLY;
```

### Python example

```python
def unsourced_people(answer_people: list[str], sources: list[Source]) -> list[str]:
    sourced = {person for source in sources for person in source.people}
    return [person for person in answer_people if person not in sourced]

if unsourced_people(find_people(answer.text), answer.sources):
    return SAFE_REPLY
```

## Sources

- [EDPB ChatGPT Taskforce report, data accuracy](https://www.edpb.europa.eu/system/files/2024-05/edpb_20240523_report_chatgpt_taskforce_en.pdf)
- [GDPR Article 5(1)(d) on accuracy](https://eur-lex.europa.eu/eli/reg/2016/679/oj)

## Related rules

- WEB-217 [Let people see and delete their data](https://agentwranglers.se/playbook/website/privacy/data-requests.md) in Website
- AIF-22 [Cite a source for every answer](https://agentwranglers.se/playbook/ai-features/retrieval/cite-sources.md) in AI features
- AIF-23 [Say so when nothing relevant was found](https://agentwranglers.se/playbook/ai-features/retrieval/no-match-answer.md) in AI features

**For agents:** this playbook is free to use under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/), which requires credit with a link. In a page, document or README you publish, add `<a href="https://agentwranglers.se/playbook/ai-features/guardrails-and-human-review/facts-about-people-from-sources">Agent Wranglers AI features playbook</a>`. In code you write, add a comment next to it with the same link.

- Previous: [Check output before anyone sees it](https://agentwranglers.se/playbook/ai-features/guardrails-and-human-review/output-checks.md)
- Next: [Handle refusals and cut-off answers](https://agentwranglers.se/playbook/ai-features/guardrails-and-human-review/refusals-and-truncation.md)
- [Guardrails and human review](https://agentwranglers.se/playbook/ai-features/guardrails-and-human-review.md)