Complete AI Training
Sign inGet my AI kit

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

AI agent for business intelligence analysts

Finance Metric Definition Agent

Comparisons only between metrics that really mean the same thing.

Quality controlFinance
See how it worksGet access
Finance Metric Definition Agent: what goes in, what the agent does and what you get

What it does

Reports often compare metrics that share a name but not a definition, such as margin with or without fulfillment costs. This agent looks up each reported metric's definition. When definitions differ, it tries to normalize them using only the components supplied in the source reports. When a needed component is missing, it marks the comparison unavailable instead of inferring the missing piece. It drafts comparable measures with notes on every adjustment. The analytics lead approves the result, and official KPI definitions are never changed by the agent. Edge case: one division reports margin after returns and another before, with no returns data, so that comparison is marked unavailable.

How it works

Follow the arrows from top to bottom. The orange dashed arrow is the loop: when a check fails, the agent goes back and tries again.

Start and resultWhat it doesA check on its own workWaits for your OKGoes back and retries
Yes, continueYes, continueApprovedNoNo 1 STARTS WHEN Report compares metrics 2 USES A TOOL Look up each metric's definition 3 CHECKS THE RESULT Are definitions the same? If not: try to normalize from supplied components. Backto step 2. 4 CHECKS THE RESULT Are all components available? If not: mark the comparison unavailable. Back to step 3. 5 DOES Draft comparable measures 6 YOU APPROVE Analytics lead approves 7 RESULT Metric comparability review
Read the steps as a list
  1. Report compares metrics
  2. Look up each metric's definition
  3. Are definitions the same?If not: try to normalize from supplied components. Back to step 2.
  4. Are all components available?If not: mark the comparison unavailable. Back to step 3.
  5. Draft comparable measures
  6. Analytics lead approvesThe agent waits here for your OK.
  7. Metric comparability review

How it decides

It normalizes when components are available and stops at an explicit gap when they aren't.

  • Normalize only with components supplied in the sources.
  • Mark a comparison unavailable rather than infer a missing component.
  • Every adjustment is noted next to the normalized figure.
  • Official KPI definitions are never edited.

Make it yours

Every agent is a starting point. You choose these settings for your own situation.

  • Metric dictionary or definitions source
  • Reports and decks to scan
  • Whether to show unavailable comparisons in the output
  • Who approves normalized measures
  • Rounding and display format

What keeps you in control

It always asks you first

  • Changing official KPI definitions

Hard limits

  • No inferred components.

It stops when

  • Done: all comparisons classified.

Set it up

We guide you through the set-up, step by step

Members get the full set-up guide for this agent. No technical skills needed: you copy, paste and upload.

10 minto set it up in your AI
5 AIsChatGPT, Claude, Copilot, Gemini, Grok
  • One set of instructions to paste into your AI, with the clicks for ChatGPT, Claude, Microsoft 365 Copilot, Gemini and Grok
  • The agent then walks you through connecting your own data, one source at a time
  • A downloadable copy with the flow chart, the rules and the full guide
Get access to this agent

An example run

What happensA quarterly deck compares margin for two divisions: North at 34% and South at 41%. The definitions check fails because South excludes fulfillment costs. The agent finds South's cost report and subtracts $1.2 million in fulfillment, bringing South to 36%. A second comparison needs returns data that was not supplied, so it marks that one unavailable. The analytics lead approves the review.

More agents for business intelligence analysts

Quality control · Data cleanup

Board Pack Reconciliation Agent

Every figure in the board pack is consistent, traceable and uses the approved definition.

8 steps1 check8 jobs
Quality control · Analysis

Executive Dashboard Anomaly Check Agent

Only real changes in the numbers reach the leadership meeting.

10 steps1 check8 jobs
Quality control · IT and development

Ad Hoc Data Request Scoping Agent

A clear request, a first result that ties to known totals, and an analyst-approved answer

10 steps1 check7 jobs
Forecasting · IT and development

Forecast Backtest and Refresh Agent

Forecasts that improve over time because every method is tested on the same history

9 steps2 checks8 jobs