Idea Ripper // ArchiveCards: 1555 [Live] | Updated: 2026-10-14
Card #c20IR // #c20Synthesis

Large Language Models in finance are best understood as part of a pipeline rather than as a point solution. Raw documents, time series, and market feeds are curated, normalized, and embedded; retrieval layers keep knowledge current; generation is constrained by financial identities, accounting rules, and risk limits; policies are aligned and evaluated; and decisions are executed within a framework of governance and oversight.

— In our words · Source: Large Language Models in Finance (Miquel Noguer i Alonso)

[Use when]

When a team frames an LLM project as 'pick the best model,' reframe the plan around the pipeline: curation, retrieval, constraint, alignment, governance.

[Why it matters]

Upgrading the model is the least interesting move in the stack: if retrieval is stale, numbers are uncited, and decisions are ungated, a better generator just produces better-looking failures faster. Budget and scrutiny should flow to the pipeline joints, not the model checkpoint.

Related principles

#c21The architecture has four layers, illustrated in Figure 11.1 . Evidence and assurance flow upward from infrastructure and behavior to risk…When designing or auditing a financial LLM system, verify all four layers agree — infrastructure, behavior,…

More from Large Language Models in Finance

#c13Prediction and agency should not be conflated. A credit model can estimate the probability that a borrower breaches a covenant. An agentic…Use when a team proposes a stronger model as the fix for an agent that lacks memory, permissioning, or an… #c14The technically and institutionally mature objective is bounded autonomy : the agent can plan, retrieve, calculate, and propose actions…Use when deciding what an AI agent is permitted to do in production: which actions stay read-only, which need… #c15This principle prevents a common category error. A model that says it will respect a mandate has not yet respected the mandate. A model…Use when a vendor demo, benchmark score, or red-team chat log is being offered as proof that an agent is safe…