A live financial model, without the FP&A hire

It builds your monthly financials from QuickBooks and your billing data — cash, runway, margin, and a plain-English read on what changed and why. Macro benchmarks are layered in automatically, every number cites the ledger line it came from, and a second, independent senior AI reviews each monthly narrative before it ships. Built for SaaS, services, and agencies — not inventory-heavy operations.

Trained on

your QuickBooks or Xero ledger + Stripe subscription events + your versioned assumption ledger + macro benchmarks (Fed funds rate, wage and SaaS-sector data)

Methods

A driver-based forward model auto-derived from your books — no manual categorising
Every default cited to a public benchmark, not a guess
Macro benchmarks layered in automatically and flagged when an assumption drifts out of range
An append-only assumption ledger — every edit a new version with author, time, and rationale
A second, independent senior AI reviews every monthly narrative; disagreements come to you
Read-only across every connected account — no write tokens, ever

Who it's for

Founders and finance leads at SaaS, services, and agency businesses without an in-house FP&A hire.

From $599/mo

Choose a plan Try the sample

How it works

From signup to the first send.

Connect QuickBooks or Xero and your Stripe billing — read-only, in a couple of clicks.

It detects your business shape and builds a driver-based forward model, every default cited to a benchmark.

Each month it narrates what drifted from plan and why, with every number tied to a ledger line.

A second, independent senior AI reviews the narrative before it reaches you or your board pack.

Capability matrix

Does well, with review, won't do.

Out-of-scope tasks escalate · they don't hallucinate

Does well

A driver-based forward model built from your books
Cash, runway, and margin with every number cited
A monthly plain-English read on what drifted and why
Macro benchmarks layered in and drift flagged
Named scenarios on demand — 'what if I raise at 15% dilution'

With review

Every monthly narrative gets a second senior review
Out-of-range assumptions pause auto-send for your review
Reviewer disagreements come to you to decide

Won't do

Never closes books or posts journal entries
Never emits a number it can't cite to a ledger line
Never drafts fundraising material

Connections

Per tool: why we need it, what we do, how it's audited.

Connect what you need, when you need it. The assistant only reads tools you explicitly link — never the rest of your stack.

What you connect the minimum to start

Your accounting — QuickBooks or Xero, read-only.
Your billing — Stripe, for cohort and retention context.
Optional: your CRM, bank, or card accounts — for pipeline and a 13-week cash forecast.

What we handle for you no setup on your side

We auto-derive the driver model and rebuild it from your current assumptions on every refresh.
We overlay live macro benchmarks and flag any assumption sitting outside its range.
We run a second, independent senior review on every monthly narrative before it ships.

Read-only across every connected account — we hold no write tokens and reject any ledger write.

What it reads on every task

Your data. Not the public internet.

Loaded fresh per task — change a doc, the next task picks it up. No retraining, no week-long fine-tune, no stale snapshot.

Your assumption ledger — append-only, every assumption with author, time, rationale, and prior version
Your macro snapshots — the daily Fed funds rate plus wage and SaaS-sector benchmarks
Your monthly drift narratives — each run writes one reviewed, source-cited row per assumption
Your saved scenarios — named what-ifs with their assumption deltas and runway impact

Guardrails

When it stops and asks you.

Every monthly narrative — reviewed by a second, independent senior AI before it ships; the board sees it, so the bar is the strictest in the workforce
An assumption more than 20% off its macro benchmark — banners the variance and pauses auto-send for the month
A disagreement between the assistant and its independent reviewer on drift direction — routed to your inbox instead of auto-resolved
Books not closed in the last 35 days, or below the reconciliation bar — the monthly refresh is refused until the gap is fixed