Operational Analytics

Features

Industries

Reference

More

Start now
  1. Operational Analytics
  2. Agent
Reference

Put an AI agent to work in Operational Analytics

Use Proto to prepare and inspect operational measurement work.

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

  • Process Owner: Ask for snapshots awaiting review, then open the source and decision together.
  • Operations Analyst: Ask which collection runs failed or need reconciliation for a chosen snapshot.
  • Metric Steward: Ask for stale captures and invalid results in the current reporting period.
  • Action Owner: Ask for assigned actions due soon and their source snapshots.

What stays with a person

  • A person decides whether the evidence supports approval or publication.
  • The agent can assemble the relevant records and identify discrepancies.
  • The independent reviewer records the decision on the exact revision, and the process owner confirms release.

A person decides whether the evidence supports approval or publication. The agent can assemble the relevant records and identify discrepancies. The independent reviewer records the decision on the exact revision, and the process owner confirms release.

Set up Operational Analytics your way.

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

Start now Download Proto

How to get started