# Why Off-the-Shelf AI Doesn't Understand Money — Udi Menkes, Intuit

Source: [AI Engineer](https://www.youtube.com/watch?v=Owb8g3yDyzo)  
Feed7 permalink: https://feed7.dev/p/why-off-the-shelf-ai-doesn-t-understand-money-udi-menkes-intuit-0y6w9rk  
Published: 2026-07-29T20:00:06.000Z  
Trust: Source Linked (source_linked)

## Why Included

Intuit argues that domain context alone does not create experience. Its approach learns from verified state-action-outcome histories, using frontier models only to propose candidates.

## Source Summary

In Intuit’s study of roughly **100,000 business situations and time frames**, frontier models reduced more than half of their advice to acquiring customers or increasing revenue. The talk shows recommendations that ignored cash-flow and supplier-concentration constraints despite receiving business context.

## Practical Implication

Build domain agents from verified outcomes, not documents alone. Intuit converts records into **millions of state-action-outcome vectors**, uses an RL model to rank candidate actions, and then trains an LLM to express the grounded recommendation.

## Agent-Ready Context

In Intuit’s study of roughly **100,000 business situations and time frames**, frontier models reduced more than half of their advice to acquiring customers or increasing revenue. The talk shows recommendations that ignored cash-flow and supplier-concentration constraints despite receiving business context.

Build domain agents from verified outcomes, not documents alone. Intuit converts records into **millions of state-action-outcome vectors**, uses an RL model to rank candidate actions, and then trains an LLM to express the grounded recommendation.

Observed outcomes are not automatically causal: a business can improve after an action for unrelated reasons. Similar-company comparisons help, but the validity of the advice still depends on data quality, matching assumptions, and the chosen outcome measures.

## Connected Context

Feed7 judgment across 297 accumulated Signals:

This shifts domain-agent grounding from retrieving authoritative documents to learning from verified state-action-outcome records, while narrowing confidence in those recommendations through causal and data-quality caveats. It reinforces deterministic controls around financial reasoning but adds an upstream requirement: the action-ranking evidence itself must be valid, well matched, and tied to suitable outcomes.

- [How Kepler Built Verifiable AI for Financial Services — Vinoo Ganesh](https://feed7.dev/p/how-kepler-built-verifiable-ai-for-financial-services-vinoo-ganesh-0yqmhy7) — Kepler’s deterministic handling of financial values complements Intuit’s outcome-grounded action ranking; together they constrain both the recommendation evidence and its numeric execution.
- [Build for the Memo, Not the Demo — Shawn Chan, China Resources Holdings](https://feed7.dev/p/build-for-the-memo-not-the-demo-shawn-chan-china-resources-holdings-0i3s3oo) — Claim-level provenance and explicit uncertainty become implementation requirements when outcome correlations may not justify causal recommendations.
- [CausalForge: A Formally Grounded, Self-Improving Agentic Framework for Automated Research in Causal Inference](https://feed7.dev/p/2607-22511v1-0mgsdh3) — Both distinguish valid derivation from valid interpretation: formal or statistical machinery cannot ensure that assumptions and claims match the intended real-world question.
- [Semantic Blindness: 500,000 Sensors Confused an LLM - Raahul Singh & Vanč Levstik, Phaidra](https://feed7.dev/p/semantic-blindness-500-000-sensors-confused-an-llm-raahul-singh-vanc-lev-159c4yr) — Both replace unconstrained model inference with structured, domain-specific resolution, but Intuit grounds actions in observed outcomes rather than deterministic entity lookup.

## Context Map

- Layer: agent
- Domains: data
- Topics: harness-engineering, agent-reliability, tool-use

## Uncertainty

- Observed outcomes are not automatically causal: a business can improve after an action for unrelated reasons. Similar-company comparisons help, but the validity of the advice still depends on data quality, matching assumptions, and the chosen outcome measures.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.