> ## 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.

# Lead scoring and signal discovery

> Ask your agent to score leads using explicit, reviewable rules.

[Agent guide: CLI and SDK instructions →](/docs/plays/play-qualify-lead-fit)

## 1. Have your context ready

Have an ICP, labeled examples, available input fields, and rules for missing or contradictory signals.

## 2. Ask your agent

If the evidence or criteria are unclear, start with source research:

```deepline-prompt theme={null}
/deepline-research Identify evidence sources for the scoring or prioritization decision I describe. Separate observed facts, candidate proxies, and missing information. Check whether the evidence can be available at the decision date. Recommend a source plan and explain its coverage before collecting additional data. Do not invent scoring weights or treat source availability as proof of predictive value.
```

Once the criteria and evidence plan are clear, ask for scoring. Skip the research step when you already have reviewed sources and approved rules:

```deepline-prompt theme={null}
/deepline-scoring Prepare a Deepline lead-fit review for these examples. Translate my criteria into explicit rules and inspect the sources that can support them. Separate company fit, observed engagement, and inferred intent. Preserve evidence and missing values for every score. Compare a small labeled sample before expanding. Return proposals without automatically changing lifecycle stages or activating outreach.
```

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 score can be explained from evidence and your rule version. A proxy signal is not proof of buying intent, and missing evidence is not automatically a negative fact.

Ask your agent:

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

## Implement the reviewed policy

After reviewing the scoring rules and evaluation limits, hand the agreed policy to GTM execution:

```deepline-prompt theme={null}
/deepline-gtm Implement the reviewed scoring or prioritization policy from this conversation. Preserve the agreed model or rule version, input definitions, evidence requirements, missing-data behavior, and output contract. Reuse collected evidence where it fits. Check the Play and propose a representative pilot before expanding the job or changing CRM records. Do not tune the scoring policy silently during implementation.
```

## Check your understanding

Can a score be considered correct because its explanation sounds plausible?

> **Show the answer**
>
> No. Compare the recorded inputs, rule version, and calculation with the
> expected cases.

## Related guides

* [Signal playbooks](/docs/human/plays/signal-playbooks)
* [Enrich Company](/docs/human/plays/task-enrich-company)
* [Deepline Monitors](/docs/plays/monitors)
* [Choose a Deepline workflow](/docs/human/plays/decision-tree)


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