Skip to main content
    Use-case library
    FP&A / Plan-to-Perform

    Scenario & Stress Testing

    Generate downside scenarios across revenue, rates, FX and working capital.

    LLM workflowAutonomy: SuggestCash / Working CapitalRisk & ControlMedium effortOrg maturity: AugmentedCFOPartner / MD
    What changed

    A statistical model generates coherent downside and upside cases, flexing revenue, DSO, rates and FX together from their historical relationships. The plan model computes liquidity and covenant impact by formula, and a language model drafts the summary, so stress testing runs continuously rather than once a year.

    How it's built

    LLM workflow (rung 4 of 6). A coded control path: chain, router, parallel fan-out, evaluator-optimizer.

    Not an agent: the sequence of steps is fixed in advance, so the whole path can be tested end to end.

    A language model handles step 5. Rules: steps 1, 3 and 4 · Predictive ML: step 2.

    Autonomy: T0 · Suggest
    Surfaces information, ranks, or recommends. Changes nothing. Human role: does all the work; may ignore the system entirely.
    How it is governed
    The path is testable end to end. Each step is independently evaluable.
    What the certification exams call this
    • Anthropic (Claude Certified Architect – Foundations (CCAR-F))Workflow: models and tools on predefined code paths (chaining, routing, parallelization, evaluator-optimizer). source
    • OpenAI (OpenAI agent guidance (Agents SDK, Codex, OpenAI Academy))Orchestrating via code, which the Agents SDK calls more deterministic and predictable. source
    • Google Cloud (Generative AI Leader)Workflow agents (sequential, parallel, loop) that run steps in a fixed order. source
    • Microsoft (AI-901 (Azure AI Fundamentals) and AB-100 (Agentic AI Business Solutions Architect))Sequential and concurrent orchestration patterns, with steps in a set order. source

    How Koko classifies AI · the full ladder is taught in AI & Agentic Delivery Foundations.

    Try it

    Illustrative demo

    Worked example of "Scenario & Stress Testing" on synthetic data — edit the inputs to tailor it. Edit the inputs to tailor the output — it's baked synthetic data, so nothing leaves your browser until you run it live.

    Synthetic demo company (a ~$5B high-growth US AI SaaS) — swap in any name to tailor the output.

    What this run should concentrate on.

    Run live in Claude

    Workflow

    1. 1.RulesLoad the base plan and the variables to stress (revenue, DSO/DIO, rates, FX).
    2. 2.Predictive MLGenerate coherent downside / base / upside scenarios from the variables' historical relationships.
    3. 3.RulesCompute liquidity, covenant-headroom and FCF impact per scenario.
    4. 4.RulesHighlight breach thresholds and the earliest breach horizon.
    5. 5.Generative AIDraft a scenario summary for the CFO and treasury.

    Prompt recipe

    From the attached base plan, build downside, base and upside scenarios stressing [revenue, DSO, rates, FX]. Keep assumptions internally consistent. For each scenario, report liquidity, covenant headroom and FCF, and flag any covenant breach with its timing. List the assumptions you used. Run every calculation in code (a code-execution or data-analysis tool, or a spreadsheet), never in prose, and show the table it produced.
    Try in Ask KokoAI
    Controls required
    • Scenario assumptions documented and approved
    • Treasury/CFO review before scenarios inform decisions
    • Covenant definitions validated against agreements
    • No automated funding/hedging action without sign-off
    HomeNewsLearnIntelBuildAsk Koko