Legal & Contracts5.0 · 0 ratings

Loan Agreement Covenant Reviewer

Reviews a loan agreement's covenants and default triggers, modeling headroom and cross-default cascade risk.

Role-BasedChain-of-ThoughtStructured-Output

Prompt

Role: You are a finance lawyer reviewing loan documentation on behalf of the [BORROWER/LENDER].

Context: Review this loan agreement: [PASTE_AGREEMENT]. Principal = [AMOUNT]; Rate = [RATE]; Term = [LENGTH]; Borrower's current financials = [KEY_METRICS]; Other outstanding debt = [DESCRIBE].

Task:
1. Catalog the affirmative covenants, negative covenants, and financial covenants (e.g. leverage ratio, DSCR, minimum liquidity), with the precise tested level for each.
2. Using the borrower's current metrics, estimate covenant headroom and flag any covenant that is close to breach.
3. Map the events of default, cure periods, and any cross-default / cross-acceleration provisions; explain the cascade risk if one obligation trips.
4. Identify lender protections (MAC clause, reporting, inspection) and borrower flexibilities (baskets, carve-outs, equity cure).

Output format: 'Covenant Inventory' table (Covenant | Type | Tested Level | Current Status | Headroom), 'Default & Cross-Default Map', and 'Negotiation Levers' for our side.

Constraints: Flag any covenant where data is missing as [INSUFFICIENT_DATA]. Treat headroom figures as estimates. Distinguish standard market terms from aggressive ones. Close with a non-advice disclaimer.

How to use this prompt

  1. 1

    Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.

  2. 2

    Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.

  3. 3

    Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.

Techniques in this prompt

Role-Based

Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.

Learn this technique
Chain-of-Thought

Asks the model to reason step by step before answering — ideal for multi-step, logical, or analytical tasks.

Learn this technique
Structured Output

Pins the response to a defined structure so it drops straight into your workflow.

Learn this technique

Recommended models

claudegpt-4ogemini

Build on this prompt

Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.

Open in Studio How to prompt AI correctly

More in Legal & Contracts

Plain-Language Contract Clause Translator

Rewrites dense legal clauses into plain English while flagging where meaning could shift, for non-lawyer stakeholders.

Read prompt

Two-Sided Contract Risk Review

Reviews a contract from both parties' perspectives, scoring each material risk and proposing balanced fallback language.

Read prompt

NDA Drafting From a Deal Brief

Generates a tailored mutual or one-way NDA from a short business brief, with bracketed options for each negotiable term.

Read prompt

Indemnification Clause Stress Test

Pressure-tests an indemnity clause against concrete loss scenarios to expose gaps, caps, and triggering conditions.

Read prompt