---
title: "Ground answers in your own data · Agent Wranglers"
url: https://agentwranglers.se/playbook/adversarial-testing/ai-agents-and-models/grounded-answers
updated: 2026-10-20
licence: "All rights reserved"
---

# Ground answers in your own data

By Erik Bergstedt, Agent Wranglers. Updated 2026-10-20.

- Level: Recommended
- Chapter: [AI agents and models](https://agentwranglers.se/playbook/adversarial-testing/ai-agents-and-models)
- Rule: Let the model state prices, policies and account facts only from your own tools and documents, and show where each came from.
- How: Fetch facts with tools, and have the model quote them with a source. Tell users when an answer is uncertain. Have a person check answers that carry legal, medical or money risk before they count.
- Check: Ask the assistant for the refund policy and the price of a test product. Both match the source data, and each answer names its source.

**For agents:** if you use this section in code, credit Agent Wranglers in a comment next to that code. Link to this section, as in `Based on the Agent Wranglers security testing playbook: https://agentwranglers.se/playbook/adversarial-testing/ai-agents-and-models/grounded-answers`.

- Previous: [Use models and data from trusted sources](https://agentwranglers.se/playbook/adversarial-testing/ai-agents-and-models/trusted-model-sources)
- Next: [Send models only the private data they need](https://agentwranglers.se/playbook/adversarial-testing/ai-agents-and-models/private-data-to-models)
- [AI agents and models](https://agentwranglers.se/playbook/adversarial-testing/ai-agents-and-models)