Hire an AI company filing earnings workbook updater

Everything it can hand back

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

• A trailing 12 month bridge for each earnings line you model
• A weighted share count built for the exact period
• Reported and adjusted EPS side by side on the same share count
• A bridge from current tax expense to cash tax paid, and a check that OCI transfers net to zero
• A change log of every changed period, definition and source

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 has just filed its annual or quarterly report and your model needs to catch up.

• Trailing-period bridge. Last full year plus current year to date, less the matching prior period, for each earnings line.
• Weighted share schedule. Share count by date and days for the exact period, tied to the filing's closing shares.
• Purchased amortization EPS bridge. Reported and adjusted EPS on the same diluted shares, with the tax effect.
• Cash tax bridge. Tax expense and payables worked into cash tax paid, with any difference explained.
• OCI reclassification bridge. Equal and opposite profit and OCI entries, and proof that total comprehensive income is unchanged.
• Change log. Every changed period, definition and source, for your reviewer.

How the work is checked

• Every updated schedule points to a dated source. Additive periods and share counts are correct, tax and OCI differences reconcile, and no practice figure stands in for missing company data.
• Trace each material input to its source, date, currency, scale, sign and reporting period. Keep unresolved MISSING: lines.
• Tell a real zero, missing evidence and a ratio that does not apply apart. Never force a tie with an unexplained plug.
• Keep inputs apart from formulas. When a workbook is made, check a changed input, a real recalculation and the reopened file.
• 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

• Trailing-period financial bridge. Builds trailing figures as last full year plus current year to date, less the matching prior year to date. Keeps balances, margins and EPS out of that sum. Hands step 2 the period dates and ordinary profit.
• Weighted-average share schedule. Builds the share count for the exact trailing period from the dated ledger, weighting each stretch by days. Hands step 3 the basic count and the diluted count from the filing.
• Purchased amortization EPS bridge. Adds back purchased-intangible amortization less its recognized tax benefit, and shows reported and adjusted EPS on the same diluted shares. Hands step 5 the items it already added back.
• Current tax cash-payment bridge. Starts with opening tax payable, adds current tax expense and noncash moves, takes off closing payable, and compares to cash tax paid. Keeps deferred tax out of cash.
• OCI reclassification bridge. Moves each recycled after-tax amount into profit and out of OCI as equal and opposite entries, proves total comprehensive income is unchanged, and lists open model checks for the reviewer.

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 prepare-a-filing-based-earnings-model-update 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/prepare-a-filing-based-earnings-model-update/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 filing: annual or interim report with its notes, as a PDF or pasted text
• Your prior model, as a spreadsheet
• Annual and year-to-date income statements, with the same period last year
• A dated share ledger, and the diluted share count from the filing
• The notes on purchased intangibles amortization and its tax effect, current tax paid, and OCI items moved to profit
• Currency, scale, fiscal year end and accounting basis

Helpful context (optional)

• The prior filing, so restated lines can be compared
• A named reviewer who will read the change log

Tools and access

• A spreadsheet engine and file-capable AI: Updates a linked workbook, recalculates it and reopens the saved file to check it.
• 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.
• Excel or Google Sheets: Holds the share ledger so you can check every row and rerun the sums with your own dates.
• An AI that can make files: Builds and reopens an editable workbook. Without it you get a table to paste into a sheet.
• Node.js 20 or later (optional): Runs the bundled script as a cross-check on a case with one share issue.
• Node.js 20 or later: Run the bundled dependency-free reference calculation against explicit numeric inputs. Without it, the AI does the sums in chat.

Functions and deliverables

• Company filing earnings workbook updater: Share the new filing, prior model and supporting schedules. Get a linked earnings workbook update with period, share, tax and adjustment checks.
  • A trailing 12 month bridge for each earnings line you model
  • A weighted share count built for the exact period
  • Reported and adjusted EPS side by side on the same share count
  • A bridge from current tax expense to cash tax paid, and a check that OCI transfers net to zero
  • A change log of every changed period, definition and source
• Trailing year financial calculator: Share annual and matching year-to-date figures. Get a trailing-year sales or profit total with period checks.
  • A trailing 12-month figure built from last year, this year to date and the same period last year, with the period checks.
  • An editable workbook of the trailing twelve months, with its inputs, formulas and test cases to rerun.
  • A tie-out of the trailing figure and four quarters where available, the inputs still missing and the checks that ran.
• Weighted share count calculator: Share dated share changes and earnings. Get weighted-average shares and basic earnings per share with timing checks.
  • A dated share timeline, one row for each stretch with the same share count
  • The weighted-average share count, with the day fractions shown and checked to add to one
  • Basic EPS with the working
  • A timing test showing EPS if the biggest transaction date moves earlier or later
  • A tie-out to the filing, and a list of what is missing
• Acquired asset earnings adjustment checker: Share acquired asset charges and their tax effect. Compare reported earnings per share with an adjusted view.
  • The after-tax adjustment: amortization less its tax benefit
  • Reported EPS and EPS with the adjustment added back
  • The per-share size of the adjustment
  • A short note on what the add-back leaves out
  • A list of anything missing, and what it held back
• Cash tax payment reconciler: Share current tax expense and payable balances. Check cash paid against the reported payment and explain gaps.
  • The cash tax payment inferred from the payable roll-forward
  • The gap to the reported cash tax paid, as a signed amount
  • A short list of likely causes if the gap is not zero
  • Sources, assumptions and a list of anything missing
  • An editable workbook, if your AI can make spreadsheet files
• 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.
• 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 has just filed its annual or quarterly report and your model needs to catch up.
• Last year's figures were restated and you need to see which lines changed.
• Your trailing EPS looks off because quarterly share counts were added together.
• You are handing a model to a reviewer and need a change log that shows what moved.

Limits to check before starting

• You only need basic and diluted EPS from a share ledger: use the Basic and diluted earnings per share checker.
• You want to write the earnings preview or the note after the release: use Earnings preview, call review and written update.
• The company is private or you have no filing. This workflow needs the filing's own notes.

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 workflow pack to Claude, ChatGPT or Gemini. Use an AI that can read PDFs and spreadsheets, and that can make files if you want a workbook.
• Attach the new filing and your prior model. Add the share ledger and the tax and OCI notes. State the currency, scale and fiscal year end once.
• After step 1, check that the prior year-to-date period has the same length as the current one, and that restated lines match the filing.
• After step 2, check that the share count was built for the whole period and not added up from quarters, and that closing shares match the filing.
• After steps 3 to 5, check that adjusted EPS, cash tax and OCI each point to a filing note, and that no item is counted twice.
• Read the change log and every MISSING line before you pass the model on.
• This workflow is under the MIT licence in its LICENSE file. It checks arithmetic and is not investment, tax or accounting advice.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/prepare-a-filing-based-earnings-model-update 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.