Hire an AI toll road debt repayment modeller

Everything it can hand back

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

• Toll receipts and operating cash for each of three years
• Cash available for debt service for each year, with the basis stated
• Target debt service, interest, principal and the closing balance each year
• Any year where cash cannot cover interest, and any residual left at maturity
• Traffic and collection cases on separate lines, and checks that could not run

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 traffic study gives yearly passages and you need to know how much debt the cash can carry.

• TOLL CASH. Yearly toll receipts after collection loss, less operating cash.
• CASH FOR DEBT SERVICE. Each year's cash under the lender's definition, with the basis stated.
• REPAYMENT. Target service, interest, principal and closing debt each year, with any gap or residual.
• SENSITIVITY. Any traffic or collection case you gave, shown apart from the base.
• SOURCES, MISSING and CHECKS MISSED. Each input's source, each gap, and every check that failed or could not run.

How the work is checked

• Traffic is explicitly sourced actuals or assumptions; operating cash is converted to contract-qualified CFADS before sculpting debt. Actual receipt/payment sources do not receive a second working-capital deduction; accrual and cash-basis routes are explicitly distinguished.
• Trace each material input to its source, date, currency, scale, sign and reporting period. Retain unresolved MISSING: lines.
• Reconcile the opening debt, interest, principal and closing debt for each year.
• 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

• Toll revenue ramp model builder. Separates study assumptions from measured passages, multiplies chargeable passages by the toll and the cash share, and takes off operating cash. Hands step 2 annual operating cash and the tax, capital and working capital items left out. Check before moving on: no passage count is cut twice.
• Project cash available bridge. Converts each year's operating cash to cash available for debt service under the lender's definition. Records that operating costs came off upstream, so none is taken twice. Declares accrual or cash and never mixes them. Hands step 3 one qualifying cash figure per year.
• Debt repayment sculpting planner. Turns each year's cash into target debt service using your cover ratio, charges interest on the opening debt, puts the rest to principal, and rolls the balance forward. Shows any interest gap and the residual at maturity. Keeps traffic sensitivity apart.

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 connect-toll-operating-cash-to-debt-repayment 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/connect-toll-operating-cash-to-debt-repayment/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

• Chargeable passages for each of three years, before collection losses, marked as study assumptions or measured (from the traffic study and tolling records)
• The toll per passage and the share collected in cash (from the tariff schedule and collection data)
• Operating cash costs for each year (from your budget or accounts)
• The lender's definition of cash for debt service, with tax, capital and working capital (from the financing agreement)
• The opening debt, the loan rate, the target service cover and the principal rules (from the loan agreement)
• Whether operating figures are accrual or actual cash, and the reporting date, currency and scale

Helpful context (optional)

• The traffic study's own tables, not a summary of them.
• Billing and collection records from the toll operator.
• A named reviewer who knows the financing agreement.

Tools and access

• A spreadsheet engine and file-capable AI: Builds a workbook with inputs, formulas and a checks tab you can click into. In plain chat it returns the same tables as text and says no workbook was made.
• 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.

Functions and deliverables

• Toll road debt repayment modeller: Model toll cash and running costs. Apply the loan's cash rules, then plan repayments from the cash that qualifies.
  • Toll receipts and operating cash for each of three years
  • Cash available for debt service for each year, with the basis stated
  • Target debt service, interest, principal and the closing balance each year
  • Any year where cash cannot cover interest, and any residual left at maturity
  • Traffic and collection cases on separate lines, and checks that could not run
• Toll road revenue cash modeller: Share billable traffic, tolls and collection assumptions. Get three years of receipts and cash after operating costs.
  • Billed receipts, cash receipts and operating cash for each of the three years.
  • An editable workbook of the toll revenue model, with its inputs, formulas and test cases to rerun.
  • A tie-out of chargeable passages, receipts and operating cash, the inputs still missing and the checks that ran.
• 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
• 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 traffic study gives yearly passages and you need to know how much debt the cash can carry.
• A lender asks for repayments sized to a cover ratio on toll cash.
• You want to see what a traffic or collection drop does to the repayment profile.
• You are unsure whether operating costs are being taken off twice between your model and the lender's definition.

Limits to check before starting

• The project is paid a fixed availability payment. Use the Project contract cash flow checker workflow.
• You already have cash for debt service and only need repayments and cover. Use the Project debt repayment modeler workflow.
• You want covenant headroom tested period by period. Use the Debt service coverage checker workflow.
• You want a traffic forecast. This takes a traffic study as an assumption and does not produce one.
• You have fewer or more than three years. This 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 traffic study, toll tariffs, collection records and loan terms. Paste the lender's cash definition. Say whether your operating figures are accrual or actual cash.
• After step 1, check passages are before collection loss and that receipts equal passages times toll times the cash share collected.
• After step 2, check operating costs come off once and the basis matches your figures.
• After step 3, check interest comes first and that any shortfall or residual is shown. Fill every MISSING line. A person who knows the loan agreement should confirm the terms.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/connect-toll-operating-cash-to-debt-repayment 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.