Hire an AI project debt repayment modeler

Everything it can hand back

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

• Cash available for debt service for each of the three years
• Target service, interest, principal and closing balance for each year
• Any year where cash does not cover interest, shown as a gap
• A loan-life cover ratio and the cushion above one
• The loan balance left after the three years
• Missing facts, and checks that could not run

How it does the job well

• Start from the user problem and the evidence for it, then the solution.
• Write decisions down with the reason and the options you rejected.
• Keep scope small enough to ship and learn. Name what is out of scope.
• Define how success will be measured before building.

Mistakes it avoids

• Treating opinions or one loud request as proven demand.
• Specs that skip edge cases, error states or dependencies.
• Roadmaps with dates but no owners or confidence levels.

What a good result looks like

An example, not your task: A lender wants repayments sized to cash with a target cover ratio.

• 1 CASH AVAILABLE. Cash available for debt service for each year, with the basis and every adjustment shown.
• 2 DEBT SCHEDULE. Target service, interest, principal and closing loan for each year, with any year cash cannot cover interest.
• 3 LOAN-LIFE COVER. Discounted cash over the loan term against the loan balance, as a ratio with its cushion.
• SOURCES. Each input with its source, date, currency and scale, and the basis used.
• MISSING and CHECKS MISSED. Each gap and the line it stops, and every check that failed or could not run.

How the work is checked

• The same eligible cash series runs through all three steps; cash available is built once on a declared basis, repayments tie to target service, and loan-life cover uses the contract's discount rate and no cash beyond maturity.
• Trace each material input to its source, date, currency, scale, sign and reporting period. Retain unresolved MISSING: lines.
• Reconcile opening balances, additions, deductions and closing balances. 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 Charlie Munger would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Project cash available bridge. Builds cash available for debt service for each of the three years on one declared basis. Passes the annual series and the definition ledger to step 2. A single-year example is a method guide, not a forecast.
• Debt repayment sculpting planner. Uses that series, the opening loan and the loan rate to work out target service, interest, principal, closing balance and any interest gap. Hands step 3 the debt horizon and balance.
• Loan life cash cover checker. Discounts the same eligible cash over the remaining loan term at the contract's loan-life rate and compares it with the opening loan. Never uses your cost of capital or cash beyond maturity.

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 build-a-project-debt-service-cash-pack 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/build-a-project-debt-service-cash-pack/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

• Three annual project operating cash records, or approved scenarios (from your project model)
• Whether those figures are accrual or actual cash (from your accounts)
• The lender's definition of cash available for debt service (from the financing agreement)
• The opening loan balance, the fixed annual loan rate and the target cover ratio (from the loan agreement)
• The loan-life discount rate the agreement names, and the loan end date
• The reporting date, currency and scale

Helpful context (optional)

• The financing agreement's definitions, not a summary of them.
• Cash records marked actual or forecast.
• A named reviewer from your lender relations or finance team.

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 project financial model: It holds the three years of cash. Export it as a sheet so the AI reads real figures, not a summary.
• 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.
• Claude, ChatGPT or Gemini: Any of them can do these sums in a chat and show each step.
• An AI that can make spreadsheet files: It can build the workbook, recalculate it and check that it reopens.
• Node.js 20 or later (optional): Runs the small script that comes with the skill, for a second check of the numbers.
• Claude, ChatGPT or Gemini: Any of them can do these sums in a chat.

Functions and deliverables

• Project debt repayment modeler: Link project cash to loan repayments and check how the cash covers debt over the loan's remaining life.
  • Cash available for debt service for each of the three years
  • Target service, interest, principal and closing balance for each year
  • Any year where cash does not cover interest, shown as a gap
  • A loan-life cover ratio and the cushion above one
  • The loan balance left after the three years
  • Missing facts, and checks that could not run
• Project cash for debt checker: Share project revenue, costs and financing definitions. Check cash available for debt payments without counting cash changes twice.
  • An editable workbook with the cash available bridge, built on your stated basis.
  • A source index showing where each input came from and its date.
  • A reconciliation table that ties the bridge to source cash and the contract definition.
  • A list of missing inputs and a CHECKS MISSED list.
• Cash flow debt repayment planner: Share loan balance, cash for repayments, interest and the target coverage ratio. Get a three-year repayment plan, remaining debt and payment gaps.
  • The most debt service each year can carry at your target cover
  • Interest, principal and closing balance for each of the three years
  • Any balance left after year three, shown as a final payment due
  • A shortfall line for any year where cash flow cannot cover interest
  • A list of missing facts and checks that could not run
  • A small workbook with the same sums, if your AI can make files
• Loan lifetime cash coverage checker: Share three years of qualifying cash and loan terms. Check discounted cash coverage and the cushion over debt.
  • The value today of the cash that can repay the loan
  • The loan life cover ratio
  • The cash cushion above the loan balance, shown as plus or minus
  • A check that no cash after the loan end is counted
  • A list of missing facts and checks it could not run
  • A small workbook with the same sums, if your AI can make files
• Product context file writer: Share product facts, audience and positioning. Get a reviewed context file that other marketing skills can reference.
  • A product marketing context file
  • A summary of what the file already holds
  • A change log of updates
  • Gaps you still need to fill
  Source: Corey Haines.
• 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 lender wants repayments sized to cash with a target cover ratio.
• You want to know whether three years of forecast cash support the opening loan.
• The loan-life cover test uses a rate set in the agreement and you need it applied correctly.
• Your cash forecast mixes accrual figures with actual receipts and payments.

Limits to check before starting

• The project earns from traffic or demand, and you need to model that revenue first. Use the Toll road debt repayment modeller workflow.
• The project is paid a fixed availability payment. Start with the Project contract cash flow checker workflow.
• You already have cash available for debt service and want covenant headroom across periods. Use the Debt service coverage checker workflow.
• You have fewer or more than three years of cash. This pack is built for three annual periods.

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 the three years of project cash and the financing agreement's definitions. Paste the opening loan, rate, target cover and discount rate. Say whether the cash figures are accrual or actual cash.
• After step 1, check that all three years use one declared basis and that working capital is not taken off twice.
• After step 2, check that interest plus principal equals target service each year, and read any year flagged as a gap.
• After step 3, check that the discount rate is the contract's, not your cost of capital. Fill every MISSING line first. Nothing here pays, sends or files anything. A person who knows the agreement checks it before anyone acts.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/build-a-project-debt-service-cash-pack 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.