Skip to main content
    Use-case library
    Treasury & Liquidity

    Cash Flow Forecasting (multi-horizon)

    Roll expected L2C and S2P flows into a liquidity forecast by horizon.

    LLM workflowAutonomy: DraftCash / Working CapitalMedium effortOrg maturity: AI-EnabledCFO
    What changed

    A predictive model learns pay and collect timing by counterparty from history. Rules roll receivables, payables and known commitments into daily, weekly and quarterly horizons and test each against the policy buffer, and a language model drafts the commentary on what moved since the last forecast.

    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: 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.

    Modeled value on KokoAI

    Synthetic KokoAI figures — a demo fixture, not audited or a guarantee

    13-week forecast error (MAPE)
    12 → 4 %
    lower is better
    Recurring impact
    $6M/yr
    run-rate benefit
    Cash freed
    $200M
    one-time working-capital release
    Payback
    5 months
    ≈ 6,000 hrs/yr reclaimed

    Forecast error 12%→4% lets the precautionary buffer sit ≈$200M below today's $4.2B without breaching the $3.5B floor; redeploying it at +2% adds ≈$4M/yr and avoids ≈$2M/yr of emergency short-term borrowing.

    Run this in Claude on KokoAI's data

    Opens your own Claude with the prompt and KokoAI's 13-week direct cash forecast (first 6 weeks, synthetic) pre-loaded as text — no upload, no setup. Tailor it live to your own numbers.

    Try it

    Illustrative demo

    KokoAI's 13-week direct cash forecast. Opening cash $4.2B; the workflow rolls AR/AP/payroll into weekly horizons and flags the W4 dip against the $3.5B floor. Edit the inputs to tailor the output — it's baked synthetic data, so nothing leaves your browser until you run it live.

    Liquidity floor the forecast must not breach.

    Run live in Claude
    Sample data

    13-Week Direct Cash Forecast (first 6 weeks, synthetic) — grab the one-pager PDF (the ROI, the data, and the prompt on one sheet) to share or keep, or the raw CSV / Markdown to drag into Claude or Microsoft Copilot. The prompt hand-off above already includes the same data as text.

    Synthetic KokoAI demo data — not audited

    Run it on your own document

    Drop a PDF, Excel, Word, CSV, or text file (e.g. a 10-Q, an AR aging, an invoice register) and we'll run this use case on it. Your file is read in your browser and never uploaded — only the extracted text goes into your own Claude or Copilot.

    Choose a file or drop it herePDF · XLSX · DOCX · CSV · TXT · up to 15 MB

    Read in-browser · not uploaded · 10-Q/10-K trimmed to financials + MD&A

    Workflow

    1. 1.RulesAggregate open receivables, payables, payroll and known commitments.
    2. 2.Predictive MLPredict expected pay and collect dates from historical behavior by counterparty.
    3. 3.RulesRoll flows into daily / weekly / quarterly horizons with confidence ranges.
    4. 4.RulesFlag horizons where liquidity dips below the policy buffer.
    5. 5.Generative AIDraft commentary on the largest drivers of the change vs. last forecast.

    Prompt recipe

    Build a 13-week cash forecast from the attached AR, AP, payroll and commitment data. Predict timing from counterparty history, show expected vs. worst-case by week, and call out any week breaching the [minimum cash buffer]. List the top 5 drivers of the change since the prior forecast. 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
    • Forecast assumptions documented and versioned
    • Treasurer reviews before the forecast drives any funding action
    • Model accuracy back-tested against actuals each cycle
    • No automated payment/borrowing triggered without approval
    HomeNewsLearnIntelBuildAsk Koko