Topic 17 of 20 · Part V : Advanced Decision Intelligence

Multimodal AI

Many financial facts lose meaning when reduced to plain text. Treating layout as data preserves the relationships that make a number interpretable.

The control pattern

Data asset

Text, tables, charts, images and document layout

Knobs

Resolution, OCR engine, Page selection, Layout preservation, Modality balance, Cross-modal validation

Outcome

Better understanding of complex financial documents

Measurement

See how to measure this below

What it is

Multimodal AI works across text, images, tables, charts and layout. The source document is the data asset, while resolution, OCR quality, page selection, modality balance and layout preservation are knobs.

Many financial facts lose meaning when reduced to plain text: a table header may define the period for several columns, indentation may distinguish a subtotal, and a chart may reveal a trend not stated in the surrounding narrative. Treating layout as data helps the system preserve these relationships.

The goal is not merely to describe an image, but to recover financially meaningful structure without losing the context that makes a number interpretable.

The knobs in detail

Each row is one adjustable property of the data asset, and what moving it tends to do.

KnobWhat you adjustLikely effect
ResolutionHow finely pages are renderedTrades fidelity against cost and latency
OCR engineWhich extractor reads the pageSets the floor on character accuracy
Page selectionWhich pages get visual processingKeeps cost proportionate to value
Layout preservationWhether structure survives extractionRetains period headers and subtotals
Modality balanceText-native vs. vision pathsRoutes each page to the right pipeline
Cross-modal validationReconciling OCR with table arithmeticDisagreement becomes an uncertainty signal

Applied: Stocks Assistant

For Stocks Assistant, a multimodal pipeline can extract tables from filings, read investor-presentation charts, interpret scanned annual reports, and connect transcript statements with displayed guidance. Use high-resolution rendering only where needed, because processing every page visually adds cost and latency. Route text-native pages through structured extraction, and use vision on tables, charts or low-quality scans. Retain page and bounding-box provenance so a user can inspect the exact region behind a result.

How to measure it

Evidence that the knob produced the intended behaviour, rather than shifting the problem elsewhere.

  • Cell accuracy, and row/column association
  • Unit recognition
  • Chart-value tolerance
  • OCR character error rate
  • Evidence localisation : can the user find the exact region?

Common mistakes

Rendering every page at high resolution, which buys accuracy you did not need at a cost you did not budget.

Flattening tables into prose, which destroys the header relationships that define the period.