> ## 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

> Score accounts using firmographic fit, buying signals, win/loss patterns, and closed-lost context so sales can prioritize outreach.

[Human guide: work with your agent →](https://deepline.com/docs/human/plays/play-qualify-lead-fit.md)

> [!NOTE]
>
> Apply a defined scoring policy to accepted account evidence and explain each
> proposed priority.

Use this workflow when you have a list of accounts and need to decide which ones deserve sales attention first.

This page owns scoring a defined list of accounts and explaining the result. It
does not turn an individual trigger into outreach: use [signal
playbooks](https://deepline.com/docs/plays/signal-playbooks.md) and its trigger-specific guides to qualify
the evidence before activation.

The pattern is simple: enrich the account, detect the signals that matter for
your market, score it against your ICP, and write the reason back to a CSV or
CRM review file.

## When to use it

* Rank a target-account list before outbound
* Turn closed-won and closed-lost history into a better ICP score
* Find niche signals that separate good-fit accounts from noisy lookalikes
* Revisit closed-lost accounts when something material changed
* Give agents a short, inspectable reason for each score

## Run it from an agent

```text theme={"languages":{"custom":["/languages/deepline-prompt.json"]}}
/deepline-gtm Score accounts.csv against our ICP. Use company size, industry, funding stage, hiring signals, tech stack, recent news, and any closed-won or closed-lost history. Return tier, score, reason, evidence, and next action.
```

With Codex:

```text theme={"languages":{"custom":["/languages/deepline-prompt.json"]}}
codex "Score accounts.csv against our ICP. Explain each score with evidence and write scored-accounts.csv."
```

## Workflow

**1. Start with the account list**

Use domains when you have them. Company names work, but domains reduce match
ambiguity.

**2. Enrich firmographics**

Pull company size, industry, location, funding, and other structured context
with company enrichment.

**3. Detect current signals**

Check for signals that change over time: hiring, fundraising, leadership
changes, expansion, competitive mentions, product launches, and relevant
news.

**4. Compare against your own history**

If you have CRM exports, compare enriched closed-won and closed-lost
accounts. Look for signal differences that explain why deals won or lost.

**5. Score and explain**

Score each account against the ICP and detected signals. Write the tier,
score, reason, evidence URL, and recommended next action.

## Define the review output

The following fields are a suggested custom workflow contract, not a fixed
prebuilt API response. Author and validate the policy before a pilot.

| Column | Description |
| - | - |
| `company` | Company name from the input or enrichment result |
| `domain` | Resolved company domain |
| `fit_tier` | `A`, `B`, `C`, or your own tier scheme |
| `score` | Numeric score if you ask for one |
| `fit_reason` | Short explanation of the score |
| `signals` | Current signals that affected the score |
| `evidence_url` | Source URL for the strongest signal |
| `next_action` | What the rep or agent should do next |

## Useful variants

### Niche signal discovery

Use this when your ICP is too generic.

```text theme={"languages":{"custom":["/languages/deepline-prompt.json"]}}
/deepline-gtm Compare won.csv and lost.csv. Enrich each company, find the non-obvious differences between wins and losses, and turn the strongest patterns into a scoring model.
```

Good outputs include signal definitions, examples, and caveats. Avoid treating one noisy correlation as a rule. Ask the agent to show the evidence it used.

### Closed-lost recovery

Use this when a lost account may have a new reason to buy.

```text theme={"languages":{"custom":["/languages/deepline-prompt.json"]}}
/deepline-gtm Check closed-lost.csv for material changes since the loss: funding, leadership changes, hiring, expansion, competitor dissatisfaction, or a champion changing jobs. Score each account for re-engagement.
```

Route only accounts with a clear change. A lost deal with no new signal should stay out of the campaign.

### New signal detection

Use this when you know a trigger matters but do not yet have a saved play.

```text theme={"languages":{"custom":["/languages/deepline-prompt.json"]}}
/deepline-gtm For each company in targets.csv, flag evidence of hiring for RevOps, new sales leadership, and recent funding. Include source URLs and confidence.
```

Be specific. "Growth signals" is too broad. "Hiring two or more RevOps roles in the last 90 days" is usable.

## Quality rules

* Pilot on 5-10 rows before running the full file.
* Keep the scoring model small enough to inspect.
* Require evidence for every non-firmographic signal.
* Separate fit from timing. A perfect ICP account with no current trigger may still be a lower-priority account this week.
* Do not use AI to invent missing firmographics. If a field is unknown, leave it unknown.
* Treat a score as a prioritization input, not approval to contact or change a
  CRM record.

## Related pages

* [Enrich company](https://deepline.com/docs/plays/task-enrich-company.md)
* [Signal playbooks](https://deepline.com/docs/plays/signal-playbooks.md)
* [Deepline Monitors](https://deepline.com/docs/plays/monitors.md)
* [Decision tree](https://deepline.com/docs/plays/decision-tree.md)

## Verify this task

Compare scores with labeled fit, exclusion, and uncertain cases. Preserve missing evidence rather than treating it as verified poor fit.

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.