Hire an AI bond and loan repayment risk review

Everything it can hand back

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

• A first label of investment or speculation
• Average earnings cover against every fixed charge, in a bad year too
• The cushion of value behind the debt, against a bar for the type of business
• A safe, speculative or reject call, with ranked reasons and what would change it

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: You are about to lend to a business and want a test beyond "they seem solid".

• Step 1 label. Investment or speculation, with the test result that decided it.
• Step 2 earnings cover. All fixed charges, average earnings on two bases, the bar and a pass, borderline or fail.
• Step 3 cushion. Total debt, the owners' stake, the ratio against its bar, and how far the stake can fall.
• Step 4 call. Meets the bar, speculative at these terms, or reject, with ranked reasons.
• What would change the call. The facts that would move the call, and a date to test again.
• Hand-back summary. Each step's file and every MISSING line in one list.

How the work is checked

• Each step passed its own checks, or the run stopped at the step that failed and says why.
• The steps ran in order, and each one used the result of the one before.
• Nothing was invented to fill a gap. Every gap is a MISSING: line.
• Every fixed charge is in the total, and no earlier-deductions figure was used.
• 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 Benjamin Graham and Warren Buffett would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Labels the loan. Asks whether careful study promises safety of your money and a fair return at this price. If not, it says speculation.
• Tests earnings against all debt. Adds every fixed charge, averages earnings over about seven years and sets the cover against a bar that fits the business.
• Tests the cushion. Divides what the owners' stake is worth by the total debt, and reads it next to the earnings test.
• Writes the call. Checks size, record and honest accounts. It does not relax the bar for a near due date, a high rate or a pledge, and says what would change the call.

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 bond-safety-check 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/bond-safety-check/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 loan or bond terms and the price you would pay
• About seven years of the borrower's income statements (five will do)
• The borrower's other debts and lease payments
• What the owners' stake is worth, from a low share price or a fair private price (optional)
• The most you could lose without harm (optional)

Helpful context (optional)

• The borrower's debt note or the bond terms
• Its annual report, for the debts and lease payments
• A low share price from the last slump, if it is listed

Tools and access

• Claude: Keeps the four steps in one run, so each test uses the one before.
• A spreadsheet: Lets you check the cover sum and try a different rate or year range.
• Any good chat AI: Applying a fixed test and listing questions is text work. It cannot supply facts it does not have.
• A licensed financial adviser: Needed for any large or personal decision. This skill is not advice.
• Any good chat AI: The sums and the judgment are text work. It cannot fetch statements for you.
• A spreadsheet: Handy for checking the seven-year average and the totals.
• A licensed financial adviser: Needed for a large or personal decision. This skill is a method, not advice.
• Any good chat AI: The sums and the reading are text work. It cannot look up prices.
• A spreadsheet: Handy for the debt total and the ratio.
• Any good chat AI: Applying fixed rules and writing a reasoned call is text work.

Functions and deliverables

• Bond and loan repayment risk review: Review a borrower's earnings, debt and asset value. Get repayment-risk tests and a reasoned call under the source method.
  • A first label of investment or speculation
  • Average earnings cover against every fixed charge, in a bad year too
  • The cushion of value behind the debt, against a bar for the type of business
  • A safe, speculative or reject call, with ranked reasons and what would change it
• Investment or speculation sorter: Paste a purchase you are weighing and why. This investment or speculation sorter labels it and lists the questions a careful buyer asks.
  • A label: investment or speculation, with the reasons
  • What you would own in the thing, in plain words
  • A rough value as a range, with its assumptions, set against the price
  • The questions a careful buyer asks, with what you know and what you do not
• Debt and preferred dividend coverage checker: Share earnings, debts and fixed payments. Get coverage ratios, stress checks and a verdict under the method’s stated limits.
  • A table of every fixed claim and the total yearly charge
  • Average cover on two bases, with the bar and why it was chosen
  • Notes on the trend, worst year, latest year and refinancing rate
  • How far earnings can fall before cover reaches 1.0
  • A pass, borderline or fail with the facts that would change it
• Debt protection ratio checker: Test the equity cushion ratio before you lend. Give it the borrower's debts and its owners' stake value. You get the ratio, the bar and the weak spot.
  • Total debt and what it contains
  • The cushion and how it was valued
  • The ratio, the bar and the reason for it
  • A reading of the cushion and earnings tests together
  • How much the pledged assets count, and the weak spot
• Lender safety verdict writer: Get a clear call on loan safety: meets the bar, speculative or reject. Paste your test results and loan terms to see the reasons and what would change it.
  • The results in three lines
  • A yes or no on each exclusion check
  • Notes on the due date, rate, pledge, rate risk and price
  • One call with ranked reasons and what would change it
  • A date to test again
• 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
• Benjamin Graham: Learn to separate price from value using Benjamin Graham’s recorded frameworks. Check the evidence, the downside and the room for error.
  • Your problem worked on the way Benjamin Graham would: their questions, their method, their push-back
  • The answer or the work, in Benjamin Graham's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Warren Buffett: Review a business using Warren Buffett’s recorded principles. Check how it earns, what protects it, how managers use cash and which facts remain uncertain.
  • Your problem worked on the way Warren Buffett would: their questions, their method, their push-back
  • The answer or the work, in Warren Buffett'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

• You are about to lend to a business and want a test beyond "they seem solid".
• You are looking at a bond, a note or a preferred share and want to know how well it is covered.
• A borrower offers a high rate, a short term or collateral to make up for thin numbers.
• You already hold a loan and a new set of accounts has just come out.

Limits to check before starting

• You are weighing a share, not a loan: use Stock valuation margin-of-safety reviewer.
• You want to know if the business is worth owning for years: use Long-term business quality reviewer.
• You only have a year or two of accounts. The average needs about seven years, and five will do.
• You want to be told what to buy or how much to put in. Ask a licensed adviser. This gives a call on one loan.

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 handoff pack. It's a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Paste the loan terms, the price you would pay, why you like it, and the borrower's income statements and debts.
• It runs four steps and saves each result. A missing figure is marked MISSING, never guessed.
• Read the final call first, then the cover and cushion tests behind it. Run it again when new accounts come out.

Read it as data

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