Hire an AI revenue comparison reviewer

Everything it can hand back

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

• A revenue change log. Each change in period, currency, business or presentation shows its source, date and effect on growth.
• A linked workbook of reported revenue and like-for-like revenue. Each adjustment is applied once, in a stated order.
• A gross-to-net bridge, if the way sales are shown changed
• A residual line for any difference nobody can explain, kept apart from acquisitions and currency
• Reviewer questions for anything missing, plus MISSING lines, checks that could not run and a record for next time

How it does the job well

• Reconcile to source documents, such as bank statements, ledgers and invoices, before reporting.
• Show the calculation, inputs and period for every figure.
• Label actuals, estimates and forecasts clearly.
• Send tax, legal and regulatory questions to a qualified professional.

Mistakes it avoids

• Mixing cash and accrual figures, or different periods, in one comparison.
• Rounding or formula errors that do not tie back to totals.
• Giving personal investment advice.

What a good result looks like

An example, not your task: A company reports new quarterly or annual revenue and you want growth on a like-for-like basis.

• Changed since last review. Each new period, restatement, business, currency or presentation change, with its filing page and date.
• Trailing revenue. Last full year plus year to date less the same period a year ago, on one basis, keeping every fiscal boundary.
• Currency, business and extra-week adjustments. Each adjustment applied once in a stated order, using the company's own rate rule and notes.
• Gross-to-net bridge (only if presentation changed). Gross billings less returns, rebates and collected taxes, tied to reported revenue.
• Bridge to reported revenue. Comparable revenue stepped back to reported revenue, with any unexplained residual shown by itself.
• Growth labels. Each "organic" or "constant currency" figure shown with the company's own definition.

How the work is checked

• Every period, business and currency bucket appears once. Each adjustment appears once, in a stated order.
• Comparable revenue bridges back to reported revenue. Any unexplained difference is a residual, not a label.
• Every organic or constant-currency figure carries the company's own definition.
• No period mixes a quarter with a year to date, or two calendars.
• 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

• Compares with the last review. Reads the saved record if it belongs to this company, or sets a first baseline. Compares fiscal periods, businesses, currencies and definitions with the record. If nothing changed and no review is due, it says so and stops.
• Builds trailing revenue. Adds the last full year to the current year to date, and takes off the same period a year ago. It keeps every fiscal boundary and every restatement.
• Removes currency effects. Uses the same period and currency buckets and one stated exchange rate rule. It rebuilds revenue in comparable currency. It does not apply one currency percentage to everything.
• Adjusts for businesses bought or sold. Applies the documented acquisitions and sales to the same currency-adjusted period. The top and bottom of the growth sum cover the same businesses, and no currency effect is counted twice.
• Removes extra weeks and rebuilds gross to net. Takes out an extra week still inside the period, using the company's calendar notes. If the way sales are shown changed, it rebuilds the bridge from gross billings to reported revenue first.
• Reconciles and saves the record. Ties the final like-for-like revenue back to reported revenue, adjustment by adjustment. It writes a short record for next time and keeps the old one.

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 issuer-revenue-comparability-review-assistant 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/issuer-revenue-comparability-review-assistant/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

• The new dated revenue release or restated comparison note (from the company's results page)
• Annual and year-to-date revenue by business and currency, plus the matching figures a year ago
• Details of businesses bought or sold in the periods, and any extra-week or calendar notes
• The company's own line on how it defines organic or constant-currency growth
• The gross billings, returns and rebates and the company's sales policy, if the way sales are shown changed
• Your materiality threshold, reporting date, currency and scale
• Your last accepted revenue model and its review log (optional on a first run)
• The record from the last review, pasted in (optional on a first run)

Helpful context (optional)

• Revenue by business and currency, not one group total, so each adjustment lands on the right figure.
• The company's own notes on acquisitions, disposals and the calendar.
• A named reviewer who knows the filings and will answer the questions it raises.

Tools and access

• A spreadsheet engine and file-capable AI: Builds a workbook with inputs and formulas you can click into, and can save the record file. In plain chat it returns the same tables as text.
• The company's results page: Gives the dated release, the segment tables and the growth definitions, each with a page you can cite.
• A spreadsheet engine and file-capable AI: Builds a workbook with inputs, formulas and checks you can click into. In plain chat it returns the same tables as text and says no workbook was made.
• The company's filings and deal notes: They give restated figures and completion dates. A data-site summary often leaves both out.
• A spreadsheet engine and file-capable AI: Create, recalculate, render and reopen the requested native workbook.
• Node.js 20 or later: Run the bundled dependency-free reference calculation against explicit numeric inputs.

Functions and deliverables

• Revenue comparison reviewer: Check which sales figures can be compared. Show changes in dates, currencies, business units and reporting rules.
  • A revenue change log. Each change in period, currency, business or presentation shows its source, date and effect on growth.
  • A linked workbook of reported revenue and like-for-like revenue. Each adjustment is applied once, in a stated order.
  • A gross-to-net bridge, if the way sales are shown changed
  • A residual line for any difference nobody can explain, kept apart from acquisitions and currency
  • Reviewer questions for anything missing, plus MISSING lines, checks that could not run and a record for next time
• Comparable annual revenue modeler: Build a recent-year sales total. Adjust for currency, business changes and extra weeks to compare like with like.
  • Reported trailing 12-month revenue, built from annual plus current year-to-date less prior year-to-date
  • Constant-currency revenue and a signed currency effect
  • Organic growth on one comparable business perimeter
  • Revenue with the extra week taken out
  • A walk from reported to comparable revenue, one adjustment per line
  • Missing facts, and checks that could not run
• Gross to net revenue checker: Share billings and approved deductions. Check how returns, rebates, taxes and pass-through amounts lead to reported revenue.
  • A billings-to-revenue bridge with deduction and presentation checks.
  • An editable workbook of the gross-to-net revenue bridge, with its inputs, formulas and test cases to rerun.
  • A tie-out of gross billings, deductions and reported revenue, the inputs still missing and the checks that ran.
• Revenue growth currency checker: Share sales and exchange rates for both periods. Separate sales growth from the effect of changing rates.
  • Reported growth and constant-currency growth, side by side
  • The translation effect as a signed amount
  • A table by currency showing how each figure was translated
  • A tie to reported revenue, with any residual left open
  • Sources, assumptions and a list of anything missing
• me.md builder: Answer a few questions, or let your AI use what it remembers. Get one private file that tells any AI who you are.
  • One me.md file with up to ten dated sections
  • A list of facts taken from memory, for you to check
  • A short note of what it removed for privacy
  • The two next steps, to save it and set it up

Tasks you can use it for

• A company reports new quarterly or annual revenue and you want growth on a like-for-like basis.
• A release restates last year's sales, and your model still holds the old figures.
• A company says growth is "organic" or "in constant currency", and you want to see the sums behind the label.
• A company changed how it shows sales, such as net of rebates and returns instead of gross, and the growth rate looks different.

Limits to check before starting

• You only want a trailing twelve month revenue figure. Use the Trailing year financial calculator.
• You only want growth without currency moves. Use the Revenue growth currency checker.
• You only want growth without acquisitions and sales of businesses. Use the Like-for-like sales growth checker.
• You only want to remove an extra week from a 53-week year. Use the Extra week sales growth checker.
• You want a sales forecast, a valuation or a view on the share price. It checks reported figures and gives no view.

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 pack and give it to an AI that can read files, such as Claude, ChatGPT or Gemini. For a workbook, pick one that can create spreadsheets. In plain chat it returns the same tables as text.
• Say whether this is the first run. If not, paste the record from last time and attach the last accepted model. Then attach the new release and the company's growth definitions, and give your threshold, currency and scale.
• Read "changed since last review" first. Check each restated figure, business change and calendar note against the page of the filing it came from.
• Check that the like-for-like revenue bridges back to reported revenue, step by step. Each adjustment should appear once, and no period should mix a quarter with a year to date.
• Check that every "organic" or "constant currency" label comes with the company's own definition. Then read any residual and decide if it needs a better source.
• Answer the questions or leave them marked MISSING. Nothing is filed, sent or traded.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/issuer-revenue-comparability-review-assistant 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.