Synops
Skip to content
Spanzo

An AI-native personal finance platform. Track income and expenses, hold a budget that adapts, and get insight that reads like advice instead of a pie chart.

BetaNext.jsFlutterPythonPostgreSQLLLM
The problem

Budgeting apps categorise. They don't explain.

Every finance app can tell you that you spent $847 on restaurants. None of them tell you that it happened because you moved further from the office, or that at this rate the trip you're saving for slips by two months.

  • Charts that describe the past and predict nothing.
  • Categories you spend more time correcting than using.
  • Budgets that are fixed while your life is not.
  • Insight that stops at 'you spent more than last month'.
The solution

A model that reasons over your ledger.

Spanzo builds a structured picture of your finances — recurring flows, one-offs, seasonality, drift — and reasons over it. It surfaces causes and consequences, not just totals, and the numbers are computed deterministically before the model ever sees them.

  • Transactions categorised on ingest, learning your corrections.
  • Budgets that adapt to income that varies month to month.
  • Forecasts that say when a goal actually lands.
  • Every insight traceable to the transactions behind it.
Features

What Spanzo does.

Expense tracking

Automatic categorisation on ingest. Correct it once and the model remembers — for that merchant and the ones like it.

Income tracking

Built for income that isn't a salary. Detects recurring flows, invoices, and irregular deposits without being told.

Budget management

Envelopes that rebalance against actual income rather than the number you optimistically typed in January.

AI insights

Plain-language explanation of what changed and why, grounded in your data. Every claim links to the transactions behind it.

Financial analytics

Cash-flow projection, burn rate, and runway. The metrics a CFO would use, aimed at one person's balance sheet.

Private by construction

Bank data is encrypted per-user. Nothing you own is used to train a shared model, and you can export or delete all of it.

Architecture

How it's put together.

Every layer exists because a guarantee demanded it.

  1. Clients

    Flutter on iOS and Android, Next.js on the web. One API contract, so a feature ships everywhere at once.

    FlutterNext.js
  2. Ingest

    Bank aggregation normalised into a canonical transaction shape, then deduplicated against what's already stored.

    GoKafka
  3. Analysis

    Deterministic aggregation first — totals, trends, and forecasts are computed in code, never guessed by a model.

    PythonPostgreSQL
  4. Reasoning

    An LLM narrates the computed numbers and answers questions. It reads results; it never invents them.

    LLMRAG
Product

A look inside.

Interface walkthrough coming with the next release.

Workspace overviewScreenshot pending
Detail viewScreenshot pending
Pricing

Priced to be predictable.

Indicative pricing while we finalise plans. Nothing here is a surprise later.

Free

$0forever

Enough to see where the money actually goes.

  • 2 connected accounts
  • Expense & income tracking
  • Monthly budgets
  • 3 months of history
Get started

Plus

Most popular
$8per month

The full picture, with the model on top of it.

  • Unlimited accounts
  • AI insights & Q&A
  • Adaptive budgets
  • Cash-flow forecasting
  • Unlimited history
Get started

Household

$14per month

Shared finances, separate privacy.

  • Everything in Plus
  • Up to 5 members
  • Shared goals & envelopes
  • Per-member privacy controls
Get started
FAQ

Questions, answered directly.

Does the AI see my raw bank data?

It sees aggregates and the transactions relevant to the question you asked, never a bulk dump of your history. Totals, trends, and forecasts are computed deterministically in code — the model narrates results it cannot alter.

Is my data used to train models?

No. Your financial data is never used to train shared models, and it is encrypted per-user at rest. You can export everything or delete your account outright at any time.

Which banks are supported?

We aggregate through standard open-banking providers, which covers most major institutions across the US, UK, and EU. During beta we're adding regions based on where people actually sign up from.

What makes the budgets 'adaptive'?

A fixed budget assumes a fixed income. Spanzo re-solves your envelopes against what actually arrived this month, protecting committed spend and goal contributions first, then flexing the discretionary categories.

When does it leave beta?

When forecast accuracy and bank coverage clear our bar, not on a marketing date. Beta users keep Plus pricing permanently.

Ready to try Spanzo?

Tell us about your team and we'll get you set up.