Hire an AI share valuation assumption reviewer

Everything it can hand back

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

• A scenario report with value per share for each scenario and a grid of discount rate against terminal growth
• A list of assumptions to challenge, each with the evidence for and against it
• A source ledger that ties each figure to a filing, a period and a page
• A check of the commentary for claims the evidence does not support
• MISSING lines, CHECKS MISSED 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 you follow files new results, and your valuation model still uses the old figures.

• Changed since last review. Each filing figure, price or assumption that moved, with its period, source, old value and new value.
• Scenario report. Value per share for each scenario, plus a grid of discount rate against terminal growth.
• Assumptions to challenge. Each key assumption with the evidence for it, the evidence against it and what would change it.
• Source ledger. Each figure tied to a filing, a period and a page.
• Claim check. Commentary that the filings and prices do not support, with the evidence that is missing.
• Record for next review. A short record to paste into your next run.

How the work is checked

• Scenarios use dated evidence and explicit inputs. A scenario's arithmetic is checked, or the reply says it was not.
• Every figure and date traces to a source, or is labeled as an assumption. Facts, assumptions and scenarios stay in separate lines.
• Each required check ran, or the run stops and names the check that could not pass. A clean model is not proof of investment value.
• Commentary that states a result with certainty, or ignores contrary evidence, is flagged. No personal recommendation is given.
• 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 Charlie Munger would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Compares with the last review. Reads the saved record if it belongs to this company, or sets a first baseline. Compares exchange, currency, as-of date, model version, input dates and scenario differences. If nothing changed and no review is due, it says so and stops.
• Pulls the source for each change. Uses the Source note summariser on each changed filing or exhibit to find the exact period, figure and page. It hands those sources to the scenario step.
• Runs the scenarios. Uses the valuation engine and the matching checker in the Equity research and valuation report builder on your explicit inputs. It keeps the source ledger and inspects the rendered report. Scenarios are what-ifs, never price forecasts.
• Checks the commentary. Uses the Unsupported claim spotter to read the thesis and valuation commentary against the filings, dated prices and scenario results. It flags claims made with too much certainty and missing counter-evidence. It gives no personal recommendation.
• Starts a new baseline when needed. If the exchange, currency or valuation date changed, it does not compare with the old review. It sets a new baseline and says so.
• Saves the record. Writes the small record for next time and lists what is still MISSING. It proposes a state update and keeps the old one. It corrects a failed step at most twice, then reports the blocker.

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 equity-assumption-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/equity-assumption-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 company's new filings, with its exchange and currency (from the company's investor page or the exchange)
• Dated market data, such as the share price and the date it was taken
• Your existing valuation model, and the scenario assumptions you want tested
• The as-of date, and your size limit for a material change
• The record from your last review (optional on a first run)

Helpful context (optional)

• The latest annual or interim report, with page numbers.
• A dated share price and the exchange it comes from.
• A named reviewer who knows the company and will check the sources and the assumptions.

Tools and access

• An AI that can run Python and read files: Runs the report builder's valuation engine and its matching checker, and can save the record file. In plain chat the scenario sums are marked unchecked.
• The company's filings and a dated price source: Give each figure and price a date and a page, so nothing rests on memory.
• Any good chat AI: Claude, ChatGPT and Gemini all handle a long source in one message. Claude takes the longest texts.
• An AI that can run Python and read files: The valuation engine and strict validator are scripts in the pack. Without Python you get a plan, not a checked report.

Functions and deliverables

• Share valuation assumption reviewer: Check a share valuation model when new filings arrive. Get scenarios, assumptions to challenge and source gaps, with facts and guesses kept apart.
  • A scenario report with value per share for each scenario and a grid of discount rate against terminal growth
  • A list of assumptions to challenge, each with the evidence for and against it
  • A source ledger that ties each figure to a filing, a period and a page
  • A check of the commentary for claims the evidence does not support
  • MISSING lines, CHECKS MISSED and a record for next time
• Source note summariser: Paste an article, talk or chapter into this source note summariser. You get each claim, how well it is backed, the gaps and three quotes to keep.
  • Every claim with a quote and location, and the evidence behind each rated
  • The gaps and assumptions
  • What it adds to your question, three quotes to keep, and an 80-word summary
• Equity valuation scenario reviewer: Share filings, dated market data and your valuation model. Get checked scenarios, source gaps and questions that challenge the assumptions.
  • A research report with the thesis, counter-evidence, risks and what to monitor
  • Valuation scenarios, with the inputs for each case shown
  • A source ledger that separates reported facts, estimates and assumptions
  • A ranked list of unsupported claims and the source each one needs
  • A list of what is MISSING and which checks were missed
• Equity research and valuation report builder: Build a stock research report with value ranges, source checks and clear assumptions from company filings and a dated share price.
  • A research report in HTML with the thesis, counter-evidence, risks and what to monitor, each fact tied to a source
  • Valuation scenarios with the inputs for each case shown
  • Labels that separate reported facts, estimates and assumptions, with source dates
  • A validator result on structure, valuation and source trail
  • A PDF version of the report, if you ask for it
  Source: evilhill.
• 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
• Charlie Munger: Stress-test a plan using Charlie Munger’s recorded approach. Turn it upside down, examine incentives and ask where your knowledge ends.
  • Your problem worked on the way Charlie Munger would: their questions, their method, their push-back
  • The answer or the work, in Charlie Munger'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

• A company you follow files new results, and your valuation model still uses the old figures.
• A new share price or market exhibit arrives, and you need to know which scenarios it moves.
• You change a growth, margin or discount rate assumption and want it challenged before you rely on it.
• The exchange, currency or valuation date changed, and the old model no longer fits.

Limits to check before starting

• You want a first valuation report for a company. Use the Equity research and valuation report builder.
• You want a buy or sell view, a price target or a fairness opinion. It gives none. Speak to a licensed adviser.
• You only want to test an investment argument against opposing evidence. Use the Investment argument and contrary-evidence review.
• You want live prices. It uses no market-data feed, so you must supply dated prices.

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. An AI that can run Python works best, because the valuation engine and its checker are Python scripts. In plain chat it still works, but it marks the scenario sums as unchecked.
• Say whether this is the first run. If not, paste the record from last time. Then attach the new filings, the dated prices and your model.
• Read "changed since last review" first. Check each changed figure against the filing page it names.
• Read the assumptions to challenge. Take the two that move the value most and check the evidence for them yourself.
• Read the scenarios as what-ifs, not forecasts. Check that each scenario's inputs match the assumptions you gave.
• Fix every MISSING line. Run it again when a new filing, price date or assumption arrives. Installing it sets up no schedule.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/equity-assumption-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.