> ## Documentation Index
> Fetch the complete documentation index at: https://deepline.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Visualize a saved result

> Ask your agent to turn an existing result into a reviewable chart.

[Agent guide: CLI and SDK instructions →](/docs/sdk-v2/visualize-data)

## 1. Have your context ready

Have the saved output file and one question the chart should answer. State the intended row grain and any denominator.

## 2. Ask your agent

Paste this into your agent, then provide your task and example inputs when it asks:

```deepline-prompt theme={null}
/deepline-gtm Create a visualization from this Deepline result file. First inspect its columns, row count, missing values, and row grain. Ask me which decision the chart should support. Explain the filters, denominator, units, and treatment of unresolved records. Use the saved output rather than rerunning provider calls. Show the chart alongside the numbers used to build it.
```

Complete any requested sign-in yourself. Give the agent the missing information before approving execution. Provider-backed work can incur usage.

## 3. Review the result

The plotted totals reconcile to the inspected file. Unknown values remain distinct from zeros, and labels identify the population and units.

Ask your agent:

```deepline-prompt theme={null}
/deepline-gtm Compare the result with the acceptance rule we agreed. Show the evidence for accepted and rejected outcomes, unresolved questions, and recorded Deepline usage where work ran. If work is still running or a response is uncertain, inspect the original saved execution before proposing another request. Explain the next decision I need to make.
```

Approve a larger job, recurring work, or external changes only after reviewing that decision.

## Check your understanding

Can a chart of nonempty segments establish that every input row was processed?

> **Show the answer**
>
> No. Reconcile source IDs and exception states separately. Missing values can
> disappear from a default grouping.

## Related guides

* [Batch CSV enrichment](/docs/human/sdk-v2/batch-csv)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.