Hire an AI equity and residual income reviewer

Everything it can hand back

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

• A change log of each movement in common equity, with its source and effect on beginning book
• A book equity roll-forward that ties from opening to closing
• A residual income bridge that charges each period on its beginning book
• OCI items shown apart, with any reclassification reconciled
• A stable price-to-book scenario, labelled as a scenario
• A workbook that links back to the filings, and a short record for the next review

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 filed a new quarterly or annual report and you want to update your residual income model.

• Change log. Each movement in common equity since the last review, with its source, effect on beginning book and whether it is above your threshold.
• Book equity roll-forward. Opening book to closing book, with profit, OCI, dividends, buybacks and issues each shown, checked against the filing.
• OCI bridge. Only if recycling changed. The after-tax amount moved between OCI and profit, with total comprehensive income unchanged.
• Residual income bridge. Each period charged on its beginning book at the cost of equity, set against matching ordinary profit. Dirty-surplus items are shown apart.
• Stable price-to-book scenario. A scenario from stated return, growth and required return, labelled as a scenario and kept apart from the historical residuals.
• Record for next review. A small block with attribution, beginning book, equity charges, owner transactions, OCI exceptions, stable assumptions and source versions.

How the work is checked

• Book equity rolls forward from opening to closing and matches the filing, or the gap is shown and explained.
• Each period's equity charge uses beginning book and the cost of equity.
• An OCI change is counted once. Recycling leaves total comprehensive income unchanged.
• The stable price-to-book scenario stays apart from the historical residuals.
• 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

• Reads the last record. Uses the saved record or sets a first baseline. The record holds common-owner attribution, beginning book, equity charges, owner transactions, OCI exceptions, stable return and growth assumptions, and source versions.
• Checks the trigger. New evidence on common equity, comprehensive income or capital returns was supplied. Changes below your threshold are logged and left alone. If nothing changed, it says so and stops.
• Rolls book equity forward. The Book value per share roll-forward proves opening and closing common equity. OCI and capital movements are identified, so book change is not assumed to equal retained earnings.
• Reconciles OCI if recycling changed. The OCI reclassification bridge reconciles the permitted after-tax amount before residual income is updated. Dirty-surplus changes are never forced through earnings.
• Bridges residual income. The One-period residual income bridge charges each period on its beginning book and matching ordinary income. Dirty-surplus items are reconciled apart.
• Builds the stable scenario. The Justified price-to-book scenario is built only after clean surplus and feasible retention are documented. It is labelled a scenario, apart from the historical residuals.
• Saves the record. Writes the workbook and the new record, keeps the old record, and lists MISSING lines and CHECKS MISSED.

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 common-equity-residual-income-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/common-equity-residual-income-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

• Your prior accepted model and its last review record
• The new dated filings, with the pages on equity, comprehensive income, dividends and buybacks
• Notes on what changed in the sources since the last review
• Your materiality threshold, which is the size of change that counts for you
• The reporting currency, the scale, the fiscal calendar and the accounting basis
• The cost of equity and the forward return and growth assumptions, each with its source (from your accepted model)

Helpful context (optional)

• The statement of changes in equity and the notes on OCI.
• The company's capital return policy, if it states one.
• A named reviewer who checks the accounting basis.

Tools and access

• A spreadsheet engine and file-capable AI: Builds a workbook with inputs and formulas you can click into, recalculates it, reopens it and saves the record. In plain chat it returns the same tables as text.
• The company's own filings: The equity statement and notes give opening and closing book and every owner transaction.
• 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 own filings: They give the real equity movements. A data-site summary often hides buybacks and OCI.
• 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

• Equity and residual income reviewer: Review new equity records against the accepted model. Recheck earnings after the required return and keep future value cases separate.
  • A change log of each movement in common equity, with its source and effect on beginning book
  • A book equity roll-forward that ties from opening to closing
  • A residual income bridge that charges each period on its beginning book
  • OCI items shown apart, with any reclassification reconciled
  • A stable price-to-book scenario, labelled as a scenario
  • A workbook that links back to the filings, and a short record for the next review
• Equity and residual income modeler: Track changes in owners' equity. Check earnings left after the required return, then model a separate future value case.
  • Book equity rolled forward, with every movement named and tied to the balance sheet
  • Book value per share from closing shares
  • Residual income for each period: earnings less the charge on opening book equity
  • Dirty-surplus items listed apart from earnings
  • A justified price-to-book scenario, labelled as a scenario
  • Missing facts, and checks that could not run
• Profit and OCI transfer checker: Share profit, OCI and an allowed transfer. Check that the move leaves total comprehensive income unchanged.
  • An after-tax table of profit and OCI before and after the move, with a check that total comprehensive income is unchanged.
  • An editable workbook of the OCI reclassification, with its inputs, formulas and test cases to rerun.
  • A tie-out of total comprehensive income before and after, the inputs still missing and the checks that ran.
• 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 filed a new quarterly or annual report and you want to update your residual income model.
• The company bought back or issued shares, or changed its dividend, and book equity moved.
• Other comprehensive income changed, such as a hedge or a pension item, and you need to know if it was recycled to profit.
• You want to know whether a change is big enough to matter, using your own threshold.

Limits to check before starting

• You have no accepted model yet. Build one first with the Equity and residual income modeler workflow.
• You want growth, margin or discount rate assumptions challenged. Use the Share valuation assumption reviewer.
• You are checking revenue disclosures across periods. Use the Revenue comparison reviewer.
• You want a buy or sell view, a price target or investment advice. It gives none. Speak to a licensed adviser.
• You need live prices or market data. It uses only the filings and notes you give 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.

• Add the agent with the pieces it uses, the Build a clean-surplus residual income model workflow and the OCI reclassification bridge. If your AI cannot open them, paste both in with the agent.
• Say if this is the first run. If not, paste last time's record. Attach your accepted model and the new filings. State your threshold, currency and scale once.
• Read the change log first. Check the roll-forward by hand. Opening book, plus profit, plus OCI, less dividends and buybacks, plus issues and any other listed movement, should equal closing book in the filing.
• Check any OCI item marked reclassified against the filing's note. Fix every MISSING line.
• Treat the stable price-to-book result as a scenario, not a forecast. For a workbook, use an AI that can build, recalculate and reopen a spreadsheet. In plain chat you get tables and keep the record.

Read it as data

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