> ## 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.

# Research accounts with source evidence

> Ask your agent to build a cited account-research file for your team.

[Agent guide: CLI and SDK instructions →](/docs/guides/account-research-automation)

## 1. Have your context ready

Have account IDs, the research questions, allowed sources, and a definition of sufficiently current evidence.

## 2. Ask your agent

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

```deepline-prompt theme={null}
/deepline-research Research these accounts with Deepline for the decision I describe. Separate facts from hypotheses. Preserve source URLs, available observation dates, account identity, and evidence for each claim. Mark missing or conflicting facts explicitly. Inspect supported sources and propose a small pilot before provider work. Return a review file without creating CRM updates or outbound messages automatically.
```

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

Every material claim has relevant source evidence. The report distinguishes a source failure from an unanswered question and does not present a hypothesis as fact.

Ask your agent:

```deepline-prompt theme={null}
/deepline-research 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.

## Turn the findings into a workflow

If the research answers your question, keep the cited report. If you need a repeatable workflow, carry the reviewed findings into execution:

```deepline-prompt theme={null}
/deepline-gtm Use the reviewed research findings and source plan from this conversation to implement the agreed workflow. Preserve the evidence, source limitations, and acceptance rules. Reuse retained results where appropriate. Explain remaining gaps and propose a bounded pilot before starting additional provider work. Do not repeat source discovery without a specific unresolved question.
```

If the next step is to define or evaluate an account score, use [the scoring guide](/docs/human/guides/account-scoring-workflows) before implementation.

## Check your understanding

Does increased hiring prove that the account intends to buy your product?

> **Show the answer**
>
> No. It supports a research hypothesis. Preserve the observation and identify
> the unanswered question.

## Related guides

* [Write Plays](/docs/human/sdk-v2/plays)
* [Batch CSV enrichment](/docs/human/sdk-v2/batch-csv)
* [Research accounts before outreach](/docs/human/recipes/research-workflow)
* [Why CRM provenance matters](/docs/guides/data-provenance-in-crm)


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