> For the complete documentation index, see [llms.txt](https://docs.stackai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.stackai.com/technical-reference/evaluations-and-observability/run-records-node-traces-and-error-details.md).

# Run Records, Node Traces, and Error Details

Run records show what happened during an execution. Node details help locate the step that produced an unexpected value or error.

{% embed url="<https://files.gitbook.com/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FSQ1Sgy933krTyK0S4JpP%2Fuploads%2FH2KG97X9Nu2xGrA4Fw7S%2FG078.mp4?alt=media&token=6e74e327-d33b-4749-9745-e11ac11fdd43>" %}

## Before you begin

Permission to view the project’s run history.

## Run records and traces

| Term           | Definition                                                                                                                                                   |
| -------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| Run            | One execution of a project. Use its run ID to retrieve that execution’s state, input, output, and errors.                                                    |
| Trace          | Details of the steps taken during a run. Use it to locate the first unexpected input, output, or error.                                                      |
| Tool result    | The returned data or error from a tool operation. The agent should base its report on this result rather than assuming the call succeeded.                   |
| Dependency     | A value or step that another node needs before it can run correctly. Connect the source and map its output to the receiving node.                            |
| Output mapping | Selection of a node’s returned field for another step or the final interface. A successful intermediate result is not automatically visible to the end user. |

## Inspect a run and its node results

1. Find the run by its ID, time, or available filters.
2. Review the run’s input, output, and error in General. Select a node in Flow progress to inspect any recorded node-level values.

<figure><img src="https://1957915746-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FSQ1Sgy933krTyK0S4JpP%2Fuploads%2FzRir8InJJzrZGziYHaM9%2Ffailed-run.png?alt=media" alt="Failed run with a populated input and Code error traceback" width="485"><figcaption><p>The failed run records the submitted input and identifies Code as the failing node. Output is N/A because the run stopped before producing a final result. Read the exception in Errors before changing downstream steps.</p></figcaption></figure>

<figure><img src="https://1957915746-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FSQ1Sgy933krTyK0S4JpP%2Fuploads%2FaUbnBFwWoDvtLr8jajmP%2Fsuccessful-run.png?alt=media" alt="Successful run with populated input and calculated output" width="485"><figcaption><p>A separate successful run records both the submitted input and the returned calculation. Compare the actual output as well as the status; a Success badge alone does not establish that the result is correct.</p></figcaption></figure>

3. Trace the first unexpected value back to its source before changing downstream instructions.

You can identify the failing or incorrect step and retain evidence for diagnosis.

## Behavior and limitations

The final answer does not contain every execution detail. An empty output, an unselected branch, and a failed node have different meanings. Access to start a run does not always include access to analytics. Share run identifiers rather than copying sensitive inputs into support messages.

## Related resources

[Debug a recorded run](/guides-and-quickstarts/evaluations-and-observability/debug-a-recorded-run.md)

[Evaluation Datasets and Input Mapping](/technical-reference/evaluations-and-observability/evaluation-datasets-and-input-mapping.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.stackai.com/technical-reference/evaluations-and-observability/run-records-node-traces-and-error-details.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.