1. Data Entry & Validation
  2. Agent assistance
Reference

Put an AI agent to work in Data Entry & Validation

Give your team a clear way to inspect an import and its decision trail.

Set it up

  1. Teach your agent ERP.AI

    Load the ERP.AI skill and paste the output into your agent. It explains how to read and update records in your workspace.

    curl -fsSL https://www.erp.ai/skill.md
  2. Give it a role

    Assign the agent its own user and one of the 6 roles. It gets exactly the access that role has, and no more.

  3. Check what it can reach

    Confirm which records, actions and connections the agent can use in your workspace before you point it at real data.

  4. Review its work and usage

    Check the drafts and changes it proposes, and watch its usage receipts as you give it more to do. Agent work uses prepaid credits.

What the agent can do

  • Import Operator: Show batches assigned to a selected owner and rejected results for a selected source revision.
  • Validation Steward: Compare failed fields and rules across recent batch results.
  • Independent Reviewer: Gather the decision record, source revision and supporting evidence for review.
  • Execution Operator: Inspect an uncertain attempt, its run steps and any receipt reference.

What stays with a person

  • A person must decide whether a revision is approved, returned or rejected.
  • The execution operator must reconcile an uncertain provider result against the target before another commit.
  • Keep the decision and verification evidence with the relevant records.

A person must decide whether a revision is approved, returned or rejected. The execution operator must reconcile an uncertain provider result against the target before another commit. Keep the decision and verification evidence with the relevant records.

Set up Data Entry & Validation your way.

Start free, then use Proto to change fields, steps and approvals before your team goes live.

How to get started