Hire an AI long-term value assumption checker

Everything it can hand back

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

• A fade case: excess returns for two years by default, then none, labelled as an assumption to test
• A stable-growth case with its reinvestment rate and return on capital
• The reinvestment rate and return on capital your terminal value implies
• A note on where the three cases differ and why
• A flag if the terminal value needs returns above the cost of capital forever
• Missing facts, and checks that could not run

How it does the job well

• Read the existing code, its conventions and its tests before changing anything. Match the project's patterns.
• Make the smallest change that fully solves the request. Keep unrelated refactors out.
• Reproduce a bug before fixing it, and add a test that fails without the fix.
• Treat input from users, files and networks as untrusted. Validate it at the boundary.

Mistakes it avoids

• Claiming code works without running it or its tests.
• Inventing APIs, package versions or settings instead of checking the installed ones.
• Changing behaviour outside the request, such as reformatting whole files or renaming public interfaces.

What a good result looks like

An example, not your task: Your terminal value is most of your enterprise value and someone asks what it assumes.

• 1 FADE CASE. Economic profit year by year with excess returns fading to zero, labelled sourced or hypothetical.
• 2 STABLE CASE. Stable growth with the reinvestment rate and return on capital it needs, and what it assumes about returns.
• 3 IMPLIED BY YOUR TERMINAL VALUE. The reinvestment rate and return on capital hidden in the terminal value you proposed.
• WHERE THEY DIFFER. Each gap between the three cases and the reason, with no blended figure.
• FLAGS, SOURCES, MISSING and CHECKS MISSED. Any need for permanent excess returns, where each figure came from, each gap, and checks that could not run.

How the work is checked

• The fade, stable and implied cases are labelled and kept apart; excess returns are not assumed to last forever without evidence; differences are explained and no figure is blended across incompatible cases.
• Trace each material input to its source, date, currency, scale, sign and reporting period. Retain unresolved MISSING: lines.
• Match enterprise or equity cash flows to the corresponding discount rate.
• Keep hardcoded inputs separate from live formulas. Inspect changed inputs, actual recalculation, exported formulas and saved-file reopening.
• 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.

A second opinion

Before it hands back, your AI reviews the draft the way Warren Buffett would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Economic profit fade schedule. Builds a case where excess returns last for two years by default, then fall to zero. The two years, constant capital and no later excess return are assumptions to test, so each is backed by evidence or labelled hypothetical. Widen the case if capital changes. Hands step 2 the invested capital and NOPAT.
• Terminal growth reinvestment check. Builds a separate stable case with its reinvestment and return on capital. Says whether it assumes returns above the cost of capital forever. Is not blended with the fade case.
• Implied terminal reinvestment schedule. Backsolves your terminal value into the reinvestment rate and return on capital it implies, on the same periods, NOPAT, growth and cost of capital. Explains scenario differences instead of averaging them.

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 challenge-terminal-value-with-excess-returns 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/challenge-terminal-value-with-excess-returns/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

• Invested capital and operating profit after tax (NOPAT) for the forecast years (from your model and the filings)
• Evidence for any lasting competitive advantage, such as filings or market data (optional)
• First stable-year NOPAT and the stable growth rate (from your model)
• Your cost of capital (WACC), with its date and source
• The terminal value you propose, or the exit multiple behind it
• The reporting date, currency and scale

Helpful context (optional)

• A dated, sourced cost of capital.
• Filings or market data that support how long excess returns last.
• A named reviewer who knows the sector.

Tools and access

• 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.
• Your valuation model: Export the forecast and terminal value as a sheet, so the AI starts from your real figures.
• 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

• Long-term value assumption checker: Compare how long a business edge lasts with the growth and returns assumed in its long-term value.
  • A fade case: excess returns for two years by default, then none, labelled as an assumption to test
  • A stable-growth case with its reinvestment rate and return on capital
  • The reinvestment rate and return on capital your terminal value implies
  • A note on where the three cases differ and why
  • A flag if the terminal value needs returns above the cost of capital forever
  • Missing facts, and checks that could not run
• Economic profit value calculator: Share capital, profit forecasts and the required return. See the value of two years of excess profit.
  • A two-period economic-profit schedule and PV contribution over invested capital.
  • An editable workbook of the economic profit schedule, with its inputs, formulas and test cases to rerun.
  • A tie-out of the capital charge and each year's economic profit, the inputs still missing and the checks that ran.
• Terminal growth reinvestment checker: Share stable growth and return assumptions. Check required reinvestment, free cash flow and the resulting terminal value.
  • The reinvestment, free cash flow and terminal value for your growth rate, plus the same with return equal to WACC.
  • An editable workbook of the terminal reinvestment check, with its inputs, formulas and test cases to rerun.
  • A tie-out of reinvestment, cash flow and terminal value, the inputs still missing and the checks that ran.
• Business terminal value assumption checker: Share a terminal business value and profit assumptions. See the reinvestment and capital return those figures imply.
  • An implied FCFF, reinvestment-rate and ROC workpaper.
  • An editable workbook of the implied terminal reinvestment, with its inputs, formulas and test cases to rerun.
  • A tie-out of the backsolved cash flow and the terminal value, the inputs still missing and the checks that ran.
• AI project context organiser: Share your project and next task. Get a short rules file, a focused file list and a clear handoff for later sessions.
  • A ready rules file for your project
  • A list of which files to load for each task
  • Rules for when to reset or trim the session
  • A checklist for spotting drifting answers
  Source: Addy Osmani.
• Warren Buffett: Review a business using Warren Buffett’s recorded principles. Check how it earns, what protects it, how managers use cash and which facts remain uncertain.
  • Your problem worked on the way Warren Buffett would: their questions, their method, their push-back
  • The answer or the work, in Warren Buffett's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• Your terminal value is most of your enterprise value and someone asks what it assumes.
• A terminal value comes from an exit multiple and you want to know what growth and returns sit behind it.
• You assume a company keeps earning above its cost of capital after the forecast ends.
• A reviewer asks if your terminal growth rate fits your reinvestment.

Limits to check before starting

• You want to connect the forecast's growth to the investment it needs. Use the Growth and reinvestment spreadsheet modeller workflow. This one tests a terminal value you already have.
• You want to stress many valuation assumptions at once. Use the Equity valuation scenario reviewer workflow.
• The company has no stable end state, such as an early-stage business with negative profit. The checks assume a stable year.
• You only need the implied reinvestment from one terminal value. Use the Business terminal value assumption checker.

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 workflow pack and give it to an AI that can read files, such as Claude, ChatGPT or Gemini. Use one that can make spreadsheets if you want a workbook.
• Attach your valuation model or its schedules, and paste the terminal value, growth rate and cost of capital with their sources. Say if any figure is your own assumption.
• After step 1, check that the fade case is labelled sourced or hypothetical and that it states what it assumes about capital.
• After step 2, check that the stable case states its reinvestment rate and return on capital, and whether it assumes returns above the cost of capital forever.
• After step 3, read how the three cases differ. Fill every MISSING line before using the result in a valuation.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/challenge-terminal-value-with-excess-returns 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.