1. Impact Measurement Platform
  2. Work with Proto
Reference

Put an AI agent to work in Impact Measurement Platform

Ask for help preparing and checking a program case.

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 5 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

  • Operator: Show programs in collection whose observations are still pending and list open follow-up actions due soon.
  • Reviewer: Gather the selected program's goal, observation outcomes, document references and prior decisions for the current revision.
  • Analyst: Compare outcome values by goal and explain which program revisions have an approved decision.

What stays with a person

  • The assigned people still check source evidence and make independent review decisions.
  • A provider receipt must be verified in the external system when an action's result is uncertain.
  • Proto can organize the case for those people and show the recorded references.

The assigned people still check source evidence and make independent review decisions. A provider receipt must be verified in the external system when an action's result is uncertain. Proto can organize the case for those people and show the recorded references.

Set up Impact Measurement Platform your way.

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

How to get started