> ## 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.

# Prioritize accounts with reviewable rules

> Produce an explainable account priority queue with actions and unresolved-evidence states.

[Human guide: work with your agent →](https://deepline.com/docs/human/guides/account-prioritization.md)

Rank a small labeled account sample. Keep each reason visible so the team can challenge a priority before using it.

## Before you start

Use an authorized workspace and a small file with stable source IDs.
Have source access and your team's acceptance policy available.
This guide describes customer-authored logic, not an automatically enabled product policy.

## 1. Understand the decision

Priority combines accepted evidence with a team-defined action policy. Missing evidence is not automatically poor fit.

Test this fictional sample before calling providers:

| Case | Expected decision under this example policy |
| - | - |
| Accepted fit and relevant recent event | Apply the defined review priority |
| Size range spans two segments | Hold segment-dependent priority |
| Observed advertisement | Do not label confirmed purchase intent |

## 2. Inspect supported operations

```bash theme={"languages":{"custom":["/languages/deepline-prompt.json"]}}
deepline auth status --json
deepline search "company account signals research" --type tools,prebuilts --json
```

Inspect a returned ID with `deepline describe <returned-id> --json`.
Compare required identifiers, outputs, access mode, and price.
A similar title does not establish that a contract fits.

## 3. Implement the bounded workflow

Ask your agent to author `account-prioritization.play.ts` using [Write Plays](https://deepline.com/docs/sdk-v2/plays.md).
Have it declare the CSV input and preserve source IDs.
Reuse existing contracts when they fit the transformation.

Implement these rules explicitly:

1. Resolve account identity before attaching fit, engagement, or signal evidence.
2. Retain source dates and distinguish observations from inferred interest.
3. Apply a versioned priority rule and retain contributing reasons.
4. Propose an action and owner only where policy supports them. Preserve uncertain accounts.

Keep external changes disabled for the first pilot.
That control belongs in the authored logic, not a universal Play dry-run flag.

## 4. Check and pilot

Prepare `pilot.csv` using [CSV-safe selection](https://deepline.com/docs/sdk-v2/batch-csv.md).
Then check the source:

```bash theme={"languages":{"custom":["/languages/deepline-prompt.json"]}}
deepline plays check account-prioritization.play.ts
```

Resolve authoring errors first. After reviewing source and price, run only the pilot:

```bash theme={"languages":{"custom":["/languages/deepline-prompt.json"]}}
deepline plays run --file account-prioritization.play.ts --csv pilot.csv --watch
deepline runs get <run-id> --full --json
deepline runs export <run-id> --out account-prioritization-review.csv
deepline billing usage --run-id <run-id> --json
```

Use the ID returned by the pilot. Select a returned dataset path when several
exist. Provider-backed execution can incur usage.

## 5. Verify the outcome

Compare priorities with accepted inputs and the rule version. A changed source scope must not masquerade as a business change.

> [!TIP]
>
> Every source ID has a result or explicit exception. The fictional cases follow
> the stated policy, and actual results retain their evidence.

Ask your agent why a record was accepted, held, or rejected.
Correct the rule before expanding input or enabling external writes.

## Continue

[Account scoring](https://deepline.com/docs/guides/account-scoring-workflows.md) covers rule tests. [Advertising evidence](https://deepline.com/docs/guides/competitive-advertising-intelligence.md) limits inference.


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