One live model of your cash. Four ways to use it.
Cash Flow Copilot, Scenario Studio, Anomaly Radar, and Ask Dibein all read from the same forecast engine and the same connected data — so a number never means something slightly different depending on which screen you’re looking at.
Cash Flow Copilot
A 13-week forecast that updates itself.
Dibein reads your bank accounts and accounting ledger every day and rebuilds a rolling 13-week and 12-month cash forecast, broken down by customer, vendor, and category, with a confidence band instead of a single guess.
- Multi-entity roll-up. Forecast each legal entity separately, then consolidate into a group view with intercompany transfers netted out automatically.
- Multi-currency. EUR, GBP, USD, and CHF accounts forecast natively and convert to a reporting currency using a rate you control, not a live spot rate that moves your numbers underneath you.
- Confirmed vs. projected split. Every week of the forecast shows how much is contractually confirmed versus modeled, so you know exactly how much of your runway is a guess.
median 4-week forecast accuracy across live customers
Link bank accounts through Open Banking (Qonto, Revolut Business, N26 Business, and SEPA banks via Bridge/Powens rails) and your ledger (Pennylane, QuickBooks, Xero, Sage). Every connection is read-only — Dibein cannot move money.
The model builds a payment-timing profile per counterparty from 12–24 months of history: median days-to-pay, variance, seasonality, and how that's trended over the last two quarters.
Confirmed items (payroll, rent, signed invoices) anchor the near term. Everything else is projected from behavior and your open pipeline, with an explicit confidence interval that narrows as the date approaches.
Scenario Studio
Stress-test a decision before you make it.
Adjust hiring plans, payment terms, pricing changes, or a new loan draw against your live forecast and see the effect on cash and runway instantly, side by side with the baseline.
- Hiring plans. Model exact start dates, gross salary, employer social charges (using French and EU cost-of-employment defaults you can edit), and ramp time before productivity.
- Payment term changes. See the cash impact of moving a customer segment from Net 30 to Net 45, or renegotiating a vendor from Net 15 to Net 60, isolated from every other variable.
- Debt and credit lines. Model a draw, its repayment schedule, and interest, and see the effect on both cash and your covenant headroom in the same view.
variables you can flex in a single scenario, from DSO to headcount
Every scenario starts as an exact copy of today's forecast, not a template — so the baseline you're comparing against is always current.
Headcount and start dates, DSO/DPO shifts, one-time and recurring costs, pricing or churn changes, and debt draws or repayments — combine any of them in one scenario.
Because it runs through the same engine as the live forecast, a hiring scenario correctly compounds with payroll tax timing and your existing DSO assumptions instead of treating each input in isolation.
Anomaly Radar
Catch the transaction that shouldn't be there.
Every transaction is scored against the normal pattern for that vendor, category, and amount. Radar surfaces duplicate payments, subscription creep, and fraud-shaped outliers before month-end close, with a stated reason for every flag.
- Duplicate payment detection. Catches the same invoice paid twice, including near-duplicates with a slightly different reference or a split payment that adds up to the original amount.
- Subscription creep tracking. Surfaces recurring charges that increased silently, tools nobody uses anymore, and overlapping subscriptions across departments paying for the same category twice.
- Vendor-change alerts. Flags a change to a vendor's bank details or a first-time payment at an unusual amount — the two signals most associated with business email compromise fraud.
false-positive rate on live customer transaction volume
As transactions sync, each is compared against the historical pattern for that specific vendor and category — not a generic company-wide threshold.
Payments are matched on amount, payee, and timing window to catch duplicate invoice payments and double-paid subscriptions before they'd otherwise surface at month-end.
A vendor whose invoice amount, frequency, or bank details change from their established pattern is flagged, which is the exact shape most vendor-impersonation fraud takes.
Ask Dibein
Ask your financial data a question in plain language.
A finance-specific assistant grounded in your live forecast, ledger, and transaction history. Every answer is a number your team can trust, with the underlying transactions cited, not a plausible-sounding guess.
- Natural-language forecast queries. "What's our lowest projected cash week in the next quarter?" returns the specific week, the amount, and which assumptions drive it.
- Variance explanations. "Why is this month's spend higher than last month?" breaks the delta down by category and vendor, citing the specific transactions responsible.
- Scenario-aware answers. Ask a what-if question and it opens a pre-filled Scenario Studio draft instead of guessing at a number, so the answer is a real model, not a hallucinated one.
of numeric answers link back to source transactions or forecast rows
"Can we afford to hire two engineers in Q3?" or "Why did marketing spend jump in April?" — no query syntax or report-builder required.
The question is parsed into a structured query against your live forecast, ledger categories, and transaction history — the same data Cash Flow Copilot and Radar already use.
The response states the number and links directly to the forecast rows or transactions behind it, so anyone on the team can verify it in one click.
Works with the accounts you already use.
Every connection is read-only. Dibein can see transactions and balances; it cannot move money, change a payment, or initiate a transfer.
See the whole platform in one live playground.
No signup required — model a scenario, run an anomaly scan, and ask a question, all on a sample workspace.