Hire an AI report totals and definition checker

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A metric difference table: each number in each report, the gap and the cause
• A worked example for each gap, using your own rows
• A reporting procedure: how each number is pulled, checked and signed off
• A list of open conflicts for the metric owner to decide
• A hand-back summary with one next step

How it does the job well

• Never change a source file. Work on copies with new names.
• A shared label does not mean a shared denominator. Check what each report counts.
• A definition change needs the metric owner's approval. Until then, write PROPOSED.
• Agree the question and the decision it supports before analysing.
• Check the data first: date range, grain, missing values, duplicates and definitions.
• Compare like with like: same period length, definitions and segments.
• Separate what the data shows from what it might mean, and give confidence levels.

Mistakes it avoids

• Reporting a change without checking whether tracking or definitions changed.
• Treating correlation as cause.
• Averages that hide important segments or outliers.

What a good result looks like

An example, not your task: Finance says revenue was one number and the sales dashboard says another.

• Metric difference table. Each number in each report, the gap and its cause, such as a different date range or exclusion.
• Worked examples. One walk from the first number to the second for each gap, using your own rows.
• Reporting procedure. How each number is pulled and checked, who owns the definition and which conflicts are open.
• MISSING lines and open conflicts. Facts the AI could not confirm and decisions only the metric owner can make.
• Hand-back summary. Files saved, steps run, checks missed and one next step.

How the work is checked

• Every gap has a cause, or a line saying UNCONFIRMED or MISSING.
• Every worked example uses rows from your sources, and its steps add up to the gap or say what is left over.
• No definition is called agreed unless the owner approved it.
• The original source files are unchanged. Revised files have new names.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

Capabilities

• Spreadsheet checker. Compares the reports line by line. Finds the grain, formula, date range, exclusions and file version behind each gap. Hands the difference table and your source references to the next step.
• Process and SOP writer. Writes the reporting procedure from that table: how to pull and check each number, who owns the definition and what is still unsettled.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id align-recurring-report-metric-definitions only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/align-recurring-report-metric-definitions/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• Two or more recurring reports that show different numbers for the same metric
• The source tables or exports behind each report
• The period you are comparing, such as March
• Your written definition of the metric and who owns it (optional)
• One calculation that disagrees, such as the same month in both reports (optional)

Helpful context (optional)

• Definitions that were approved earlier.
• A named reviewer who can approve a change.

Tools and access

• A spreadsheet tool such as Excel or Google Sheets: Lets you open the difference table and re-check a formula. The AI cannot recalculate a workbook without one.

Functions and deliverables

• Report totals and definition checker: Trace why recurring reports disagree. Get a difference table, worked examples and draft rules for future reporting.
  • A metric difference table: each number in each report, the gap and the cause
  • A worked example for each gap, using your own rows
  • A reporting procedure: how each number is pulled, checked and signed off
  • A list of open conflicts for the metric owner to decide
  • A hand-back summary with one next step
• Spreadsheet checker: Check a spreadsheet for odd totals, broken formulas and messy data. Your original stays safe, and you get findings with proof and a new file.
  • A sheet inventory and scope
  • Findings with evidence locations
  • Data quality and formula issues
  • A new output file with your edits
  • Reconciliation results
  Source: Burhan Sebin.
• Process and SOP writer: Turn how your team works into a clear SOP. Give it a process name or old notes. You get a RACI table, a flow, steps and exceptions.
  • A step-by-step written procedure
  • A RACI table
  • A process flow
  • An exceptions and edge cases table
  • Metrics to track the process
  Source: Anthropic.
• Deep research reporter: Give it a research question. Get a sourced report that compares evidence, flags conflicts and lists remaining gaps.
  • A list of the sub-questions it will research
  • An executive summary
  • One section for each theme
  • Conflicts and gaps, with disputed claims labelled
  • A source list with link, author and date for each
  Source: Burhan Sebin.
• Metric definition writer: Share a metric, calculation and business use. Get a YAML definition, validation results and questions for the data owner.
  • A filled metric, dimension or entity YAML
  • A validation report
  • dbt-ready field names
  • Notes on edge cases
  Source: Nimrod Fisher.

Tasks you can use it for

• Finance says revenue was one number and the sales dashboard says another.
• A monthly report changed after someone edited a formula, and nobody can say what moved.
• Two teams both report "customers" or "active users" and the counts never match.
• You are handing a recurring report to a new person and want the rules written down.

Limits to check before starting

• You have one report and no conflict. Use the Spreadsheet checker to test its formulas.
• You need a clear definition for one new metric. Use the Metric definition writer.
• You want a new weekly report built from scratch. Use the Weekly metrics report and dashboard builder workflow.
• No one owns the metric. The AI can propose a definition, but a person must approve it.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the handoff pack. It is a zip with HANDOFF.md and the skill files this workflow uses.
• Give the folder to Claude, ChatGPT or Gemini and say "Follow HANDOFF.md".
• Attach the reports and the tables behind them. Name the metric that disagrees and the period.
• Read the difference table first. Check that each cause matches what you know about the report.
• Send the open conflicts to the metric owner. Do not change a definition until they approve it.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/align-recurring-report-metric-definitions for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.