IntelliVis Documentation

How to read this document

Sections move from purpose → concepts → calculation process → worked examples → edge cases. Formula boxes use plain mathematical notation for clarity; they are conceptual summaries, not API contracts.

• Point lists call out operator-visible behaviour.
• Callouts mark warnings, limitations, or important qualifications.
• Worked examples use round numbers so you can reproduce the arithmetic by hand.

Purpose

IntelliVis turns Insights Engine output into readable visuals: timelines, progress bars, spike comparisons, share charts, and evidence panels. The goal is explainability — you should see why a card was raised before you dismiss, snooze, or act.

• Read insight charts next to the card narrative
• Inspect evidence that points back to spending context
• Compare web and mobile renderings of the same insight
• Open underlying expenses when a visual raises a question

Where IntelliVis fits

IntelliVis is not a separate login product. It appears inside Insights Engine surfaces whenever a finding includes a chart or evidence payload. Standard Analytics charts (period trends, exports, category reports) remain part of Analytics even when Insights Engine is off.

• Insights Engine decides what to surface and when.
• IntelliVis decides how that finding is drawn and annotated.
• InteliHouse may reuse compatible chart blocks in conversation when enabled — that is still verification-first assistance.
• ReceiptVis is unrelated capture OCR; it does not draw IntelliVis insight charts.

Visual kinds you may see

Not every card includes every chart. IntelliVis selects a presentation suited to the finding. Public docs describe the kinds of visuals, not the selection algorithm.

• Cadence timelines — amounts over successive occurrence dates
• Budget progress — spend versus an effective limit
• Spike comparison — unusual period versus a baseline
• Category share — proportion views for concentration or mix
• Forecast-style bands — informational scenarios, not guarantees
• Simple line, bar, comparison, and donut layouts where they clarify the story

Evidence panels

Where available, evidence accompanies the chart so the card is not a black-box score. Evidence is a structured summary of supporting context — merchants, amounts, dates, or related categories — not a courtroom exhibit or bank statement replica.

• Use evidence to decide whether the pattern matches your household’s reality.
• Correct source expenses if the evidence shows a misclassified or duplicate row.
• Do not treat evidence snippets as complete exports; use Analytics or expense lists for full lists.

How to read an IntelliVis card

• Match currency and household scope before comparing two visuals.
• Do not infer causation from correlation (a spike near a payday is not proof of cause).
• Accessibility summaries describe the chart when present — use them on smaller screens.

What IntelliVis does not do

• It does not invent bank balances or pending authorizations.
• It does not execute trades, transfers, or tax filings.
• It does not replace Financial Health scoring or Net Worth allocation views.
• It does not grant access to data outside your permissions.

Privacy, advice limits, and what we do not publish

AccountHouse is a household tracking and organisation tool. It is not a bank, payment processor, tax advisor, or investment advisor. Forecasts, health scores, balances, and alerts are informational.

• Household data is scoped to your household; other families cannot see your ledger.
• Public documentation explains product behaviour and calculation concepts, not proprietary internals.
• Exact scoring weights, anomaly thresholds, cryptography parameters beyond high-level algorithms, and operational detection rules are reserved.
• Visuals reflect permitted household data already in AccountHouse.
• Forecast-style bands are scenarios for awareness, not promises of future spend.