Skip to main content
Human guide: work with your agent → Produce a review queue of stale or inconsistent opportunity records. Separate a proposed repair from an approved CRM change.

​
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

A missing field can require evidence, an owner decision, or an integration repair. Those exceptions need different responses. Test this fictional sample before calling providers:

​
2. Inspect supported operations

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 pipeline-hygiene.play.ts using Write Plays. Have it declare the CSV input and preserve source IDs. Reuse existing contracts when they fit the transformation. Implement these rules explicitly:
  1. Define critical fields and freshness rules for this pipeline review.
  2. Read records and supporting activity without changing them.
  3. Separate missing evidence, stale observations, policy conflicts, and access errors.
  4. Return proposed repairs and evidence without inventing stages, close dates, or commitments.
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. Then check the source:
Resolve authoring errors first. After reviewing source and price, run only the pilot:
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

Check the reason and evidence for each exception. A proposed repair is not a completed CRM change.
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

CRM repair covers controlled corrections. Revenue quality explains decision fitness.