Architecture

How WealthCues produces an answer

The whole design follows from one rule: the language model is never the source of truth. It sits at the end of the pipeline, explaining figures that deterministic code has already computed.

The pipeline

  1. 1

    Financial data

    Accounts, holdings, transactions, assets and liabilities.

  2. 2

    Normalisation

    One shape for every source, connected or manual.

  3. 3

    Calculation

    Named deterministic functions. The database is the source of truth.

  4. 4

    Retrieval

    Only the figures a question actually needs.

  5. 5

    Explanation

    Plain language over computed results, with evidence attached.

  6. 6

    Decisions

    Goals, scenarios and the things worth reviewing this month.

The layers, in order

01

Application database

Accounts, institutions, securities, holdings, transactions, assets, liabilities, goals, plans, scenarios and documents — normalised tables, not a bag of JSON. This is the only source of truth.

02

Calculation layer

Named deterministic functions: calculate_net_worth, calculate_asset_allocation, calculate_savings_rate, calculate_goal_progress, calculate_portfolio_change, calculate_cash_flow, calculate_expense_change. Same semantics in the browser and on the server.

03

Retrieval layer

Given a question, assemble only the computed figures that question needs. Nothing broader is ever put in front of a model.

04

Orchestration layer

A fixed registry of typed tools. The model chooses which to call and with what arguments; it cannot reach past them, and it never writes a query.

05

Language model

Provider-agnostic — OpenAI, Anthropic, Google or a local Ollama model. It explains computed results in plain language. It is not permitted to introduce a figure.

06

Validated response

The answer is returned with its tool calls and evidence attached, so any number on screen can be traced back to the calculation that produced it.

The 16 tools the assistant may call

This list is the complete surface. There is no general query tool and no escape hatch.

get_net_worth

Current net worth with the asset and liability breakdown.

get_recent_changes

Net-worth change over a window, attributed to its causes.

get_accounts

All accounts with type, balance, source and freshness.

get_holdings

Portfolio positions with value, cost and gain.

get_portfolio_allocation

Allocation by asset class, sector or region.

get_portfolio_summary

Portfolio value, cost, gain, day change and concentration.

get_transactions

Transactions filtered by month, category or search text.

get_spending_by_category

Spending grouped by category for a month.

get_cash_flow

Income, spending, investing and savings rate for a period.

get_goals

Goals with progress, projection and status.

calculate_scenario

Re-projects the plan with changed assumptions.

get_recurring

Detected recurring charges and subscriptions.

get_anomalies

Unusually large charges and possible duplicates.

get_insights

The generated insight set with evidence.

get_emergency_fund

Liquid cash expressed as months of spending.

get_allocation_history

A stored monthly allocation snapshot.

See it working

In the demo, every assistant reply carries a “data lookups” control. Open it to see exactly which tools were called, with which arguments, to produce that answer.

Open WealthCues AI
WealthCues

Intelligent digital tools for wealth and financial management.

Part of the ByteCues ecosystem.

Product updates

Product updates only. No financial advice, and we do not share your address.

WealthCues provides financial information, calculations and decision support. It is not financial, investment, tax or legal advice, and it makes no claims about investment returns. Demonstration figures are fictional. See Disclosures for detail.

© 2026 WealthCues. All rights reserved.