> ## 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 data

> Review enriched Play output with simple charts before you make GTM decisions or send records downstream.

[Human guide: work with your agent →](https://deepline.com/docs/human/sdk-v2/visualize-data.md)

> [!NOTE]
>
> Inspect one exported dataset and produce a small summary that preserves failed
> and unresolved rows.

Review what the workflow produced before you hand rows to sales, marketing, or
ops.

The SDK is not only for enrichment. It should help you answer:

* Which accounts are new this week?
* Which segments have the strongest signal?
* Which titles need a different workflow?
* Which rows failed and need human review?
* Which accounts should go to Salesforce now?

## Start with an output CSV

Export a completed file-backed Play before you analyze it. [Batch CSV
enrichment](https://deepline.com/docs/sdk-v2/batch-csv.md) owns the run and export procedure. This page
starts after you have `output/accounts-enriched.csv`.

Open the file first. You are looking for boring things:

| Check | Why |
| - | - |
| row count | Make sure no records disappeared |
| segment | Know which workflow path each account took |
| signal columns | See why the account is interesting |
| owner or next step | Confirm where the record goes next |
| error/review columns | Separate good output from uncertain output |

## Make a quick chart in Python

Use this when you want a fast view before building anything permanent.

```py theme={"languages":{"custom":["/languages/deepline-prompt.json"]}}
import pandas as pd

df = pd.read_csv("output/accounts-enriched.csv")
print(df["segment"].value_counts())
print(df["next_step"].value_counts())
```

That is enough to answer: “Did this workflow find the kind of accounts we wanted?”

## Common GTM views

| View | Useful when |
| - | - |
| accounts by segment | You route enterprise and mid-market differently |
| titles by seniority | VPs and directors get different plays |
| signal by source | You want to know which signal found the account |
| output by owner | You are sending tasks to Salesforce |
| failed rows | You need a human review queue |

## Keep visualization close to the workflow

Recommended folder shape:

```txt theme={"languages":{"custom":["/languages/deepline-prompt.json"]}}
workflows/
  weekly-new-accounts.play.ts
  input/accounts.csv
  output/accounts-enriched.csv
  output/accounts-summary.csv
```

The workflow creates the enriched list. The summary tells your team what changed.

## Verify this task

Check source IDs and required columns before grouping. Count unknown values explicitly rather than allowing chart defaults to hide them.

Ask your agent to explain a failed check before repeating work or expanding the scope.


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