{{organization_name}}
Organization Name
Example: Example: Meridian Trading Group
Enter the organization whose liquidity is being stress tested.
Design a Monte Carlo liquidity stress-testing framework that models uncertain cash flows, correlated market shocks, facility usage, and survival horizons.
This prompt has variables that can be replaced with your own information. Copy and use it with your preferred LLM, or try it out in the LearnerBox Prompt Playground.
Act as a senior treasury risk and quantitative finance professional.
Design a Monte Carlo liquidity stress-testing framework using the information provided below.
Organization:
{{organization_name}}
Forecast horizon:
{{forecast_horizon}}
Opening liquidity position:
{{opening_liquidity}}
Baseline cash-flow forecast:
{{baseline_cash_flow}}
Risk factors and distributions:
{{risk_factors}}
Correlation assumptions:
{{correlations}}
Facilities, covenants, and funding constraints:
{{funding_constraints}}
Analysis requirements:
1. Define the liquidity metric to be tested, including:
- minimum cash balance;
- total available liquidity;
- facility utilization;
- covenant headroom;
- survival horizon; and
- probability of liquidity shortfall.
2. Identify stochastic risk factors, such as:
- revenue;
- customer collections;
- gross margin;
- inventory;
- supplier payments;
- interest rates;
- exchange rates;
- refinancing availability;
- collateral calls;
- capital expenditure;
- tax;
- litigation or operational loss events; and
- market-value changes.
3. For every risk factor, document:
- baseline value;
- distribution;
- parameters;
- lower and upper bounds;
- timing;
- persistence;
- correlation;
- management response; and
- data source.
4. Recommend distributions only as modeling options; do not assign parameters without supplied data or approved assumptions.
5. Explain how to model correlated shocks and avoid assuming independence where risks are linked.
6. Define the number of simulations, random-seed controls, convergence checks, and reproducibility requirements.
7. Model liquidity by period under each simulation, including:
- operating cash flows;
- debt service;
- facilities;
- collateral or margin calls;
- covenant triggers;
- committed payments; and
- management actions.
8. Calculate or specify:
- probability of negative cash;
- probability of facility exhaustion;
- probability of covenant breach;
- liquidity-at-risk;
- percentile cash balances;
- expected shortfall;
- median survival horizon; and
- tail survival horizon.
9. Compare results before and after credible management actions.
10. Identify model risk, parameter uncertainty, data limitations, and omitted nonlinear effects.
11. Include deterministic reverse-stress tests to identify combinations of shocks that exhaust liquidity.
12. Do not present simulated results as forecasts or guarantees.
13. Do not invent distributions, correlations, credit availability, covenant terms, or management actions.
Present the result as:
{{output_format}}
Include:
- model objective and scope;
- risk-factor inventory;
- distribution and correlation table;
- simulation methodology;
- liquidity waterfall;
- key output metrics;
- percentile and tail-risk reporting;
- management-action overlays;
- reverse-stress scenarios;
- model limitations;
- validation checklist; and
- governance recommendations.
Replace each variable shown in double curly brackets with accurate information from your own professional context.
{{organization_name}}
Example: Example: Meridian Trading Group
Enter the organization whose liquidity is being stress tested.
{{forecast_horizon}}
Example: Example: Weekly for 13 weeks and monthly through 12 months
Specify both the horizon and time-step frequency.
{{opening_liquidity}}
Example: Provide cash, restricted cash, committed facilities, uncommitted facilities, collateral, and current usage.
Separate readily available liquidity from restricted or uncertain sources.
{{baseline_cash_flow}}
Example: Paste receipts, operating payments, tax, capex, financing, and debt-service forecasts by period.
The simulation should begin from a validated deterministic baseline.
{{risk_factors}}
Example: List each uncertain variable, historical evidence, proposed distribution, parameters, and bounds.
Use approved empirical or expert assumptions rather than invented parameters.
{{correlations}}
Example: Provide correlations or dependency relationships among revenue, collections, margin, rates, FX, and other risks.
Document both estimated correlations and qualitative dependencies.
{{funding_constraints}}
Example: List facility limits, maturities, conditions, covenants, collateral calls, and refinancing assumptions.
Funding access should be modeled according to actual contractual constraints.
{{output_format}}
Choose the format appropriate for model building, governance, or decision-making.
A rigorous Monte Carlo liquidity stress-testing design containing risk factors, distributions, correlations, simulation logic, liquidity metrics, tail-risk outputs, management-action overlays, reverse stresses, limitations, and governance controls.
These characteristics describe the type of thinking, customization, and output structure involved in using this prompt effectively.
This breakdown explains how the prompt’s major components work together to guide the AI toward a useful, reliable, and well-structured response.
Positions the AI as a treasury-risk and quantitative-finance specialist.
Defines liquidity, baseline cash flows, stochastic risks, dependencies, facilities, and horizon.
Requires a Monte Carlo framework for measuring liquidity shortfall and tail survival.
Prevents invented distributions, correlations, facility access, covenants, and forecast claims.
Requires model inputs, simulation logic, risk metrics, reverse stresses, limitations, and governance.
Organization, horizon, opening liquidity, baseline cash flow, risk factors, correlations, funding constraints, and output format.
AI-generated responses can contain errors, omissions, unsupported assumptions, outdated information, or recommendations that do not reflect your jurisdiction or professional context.
Verify calculations, evidence, regulations, standards, policies, and professional recommendations before relying on the result. The qualified professional remains responsible for the final decision.
Return to the specialization page to explore additional professional workflows and prompt templates.
Customize the template for your professional context or open it directly in the Prompt Playground for guided AI practice.