# Verifying outputs

> Verification is the habit of checking AI output before relying on it, in proportion to the cost of being wrong. This topic covers routine checking habits, following claims back to their sources, treating endorsed answers differently from raw ones, and extending "trust but verify" to actions agents take.

Page: https://schubergphilis.github.io/ai-training/topics/safety/verification/
License: CC BY-SA 4.0, https://creativecommons.org/licenses/by-sa/4.0/

*Safety* · topic `safety/verification`

Verification is the habit of checking AI output before relying on it, in proportion to the cost of being wrong. This topic covers routine checking habits, following claims back to their sources, treating endorsed answers differently from raw ones, and extending "trust but verify" to actions agents take.

## Concepts

- **Checking habits**: Small routines that catch model errors before they spread: read the output against the request you made, look for claims you did not supply, run the code, open the link, do one calculation by hand. The depth scales with stakes. A habit is better than a rule because it runs even when you are in a hurry, which is when errors slip through. [glossary](https://schubergphilis.github.io/ai-training/glossary/#checking-habits)
- **Source checking**: Following a claim, citation or quote back to where it is supposed to come from and confirming it says what the model reported. Models produce references that look right more easily than references that are right. Anything with a page number, URL, statute, version or study behind it should be opened before it goes to anyone else. [glossary](https://schubergphilis.github.io/ai-training/glossary/#source-checking)
- **Endorsed answers**: An answer that a qualified human has reviewed and marked as correct, distinct from raw model output. Some teaching and support systems show the mark so readers know which answers carry human accountability. The idea transfers to teams: separate what the model said from what a person has checked, and make the difference visible in the artifact. [glossary](https://schubergphilis.github.io/ai-training/glossary/#endorsed-answers)
- **"Trust but verify" for agents**: When an agent acts rather than answers, verification moves from reading text to checking effects: what files changed, what was sent, what was deleted. Let the agent proceed on low-stakes steps, then inspect the result against what you asked for, and require a pause before any step that is hard to reverse. Trust is granted per action, not per tool. [glossary](https://schubergphilis.github.io/ai-training/glossary/#trust-but-verify-for-agents)

## Links

- **Builds on:** [Recognizing failure](https://schubergphilis.github.io/ai-training/topics/safety/failure-modes/)
- **Leads to:** [Verifying agent work](https://schubergphilis.github.io/ai-training/topics/coding-with-agents/verification/), [Agent risk](https://schubergphilis.github.io/ai-training/topics/safety/agent-risk/), [Delegating to an agent](https://schubergphilis.github.io/ai-training/topics/using-agents/delegating/)
- **Competencies drawing on it:** [Verifies AI output before relying on it](https://schubergphilis.github.io/ai-training/competencies/safety/verifies-output/)

## Lessons

- [Asking a model to disagree](https://schubergphilis.github.io/ai-training/safety/asking-a-model-to-disagree/) (tutorial)
- [Checking habits that run when you are in a hurry](https://schubergphilis.github.io/ai-training/safety/checking-habits/) (tutorial)
- [Checking what an agent changed](https://schubergphilis.github.io/ai-training/safety/checking-what-an-agent-changed/) (tutorial)
- [Following a claim back to its source](https://schubergphilis.github.io/ai-training/safety/following-the-source/) (tutorial)
- [Marking what a person has checked](https://schubergphilis.github.io/ai-training/safety/marking-what-a-person-checked/) (explanation)

## Sources

- `CS50x` [CS50's Introduction to Computer Science](https://cs50.harvard.edu/x/), Harvard CS50 (course)
- `Liu 2024b` [Teaching CS50 with AI: Leveraging Generative Artificial Intelligence in Computer Science Education](https://doi.org/10.1145/3626252.3630938), Proceedings of the 55th ACM Technical Symposium on Computer Science Education V. 1 (SIGCSE 2024), 750-756 (paper)
- `Academy ai-fluency-framework-foundations` [AI Fluency: Framework and foundations](https://academy.claude.com/courses/ai-fluency-framework-foundations), Claude Academy (course)