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

    Driver-Based Re-Forecast

    Refresh the forecast from actuals and driver assumptions, with the changes explained.

    LLM workflowAutonomy: DraftCash / Working CapitalSpeedMedium effortOrg maturity: AugmentedCFO
    What changed

    When actuals land, the driver model re-runs by formula and attributes the change to each driver. A language model then drafts the assumption commentary, turning a multi-day re-forecast into a same-day refresh.

    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 4. Rules: steps 1, 2 and 3 · Human: step 5.

    Autonomy: T1 · Draft
    Produces a complete output for a human to review and release. Human role: reviews every item and releases it.
    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 "Driver-Based Re-Forecast" 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 latest actuals, the current forecast and the driver assumptions.
    2. 2.RulesRe-project each line from its drivers (volume, rate, mix, seasonality) by formula.
    3. 3.RulesQuantify the delta vs. prior forecast and attribute it to drivers.
    4. 4.Generative AIDraft assumption-change commentary for review.
    5. 5.HumanHand the updated forecast to FP&A for validation before publishing.

    Prompt recipe

    Given the attached actuals, prior forecast and driver assumptions, produce an updated forecast. For each major line, show the change vs. prior forecast and attribute it to the specific driver that moved. Flag any assumption that looks stale against the actuals. Do not change assumptions without listing them. 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
    • Driver assumptions versioned and owner-approved
    • FP&A validates before the forecast is published
    • Source actuals reconciled to the ledger
    • AI-drafted commentary labelled in working papers
    HomeNewsLearnIntelBuildAsk Koko