{
  "schema_version": "1.1",
  "id": "s8:https://www.youtube.com/watch?v=Owb8g3yDyzo",
  "slug": "why-off-the-shelf-ai-doesn-t-understand-money-udi-menkes-intuit-0y6w9rk",
  "url": "https://feed7.dev/p/why-off-the-shelf-ai-doesn-t-understand-money-udi-menkes-intuit-0y6w9rk",
  "title": "Why Off-the-Shelf AI Doesn't Understand Money — Udi Menkes, Intuit",
  "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.",
  "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_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.\n\nBuild 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.\n\nObserved 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.",
  "source": {
    "name": "AI Engineer",
    "url": "https://www.youtube.com/watch?v=Owb8g3yDyzo",
    "published_at": "2026-07-29T20:00:06.000Z"
  },
  "source_class": "video",
  "content_type": "Video",
  "layer": "agent",
  "domains": [
    "data"
  ],
  "topics": [
    "harness-engineering",
    "agent-reliability",
    "tool-use"
  ],
  "verification": {
    "status": "source_linked",
    "label": "Source Linked",
    "method": "source_feed",
    "verified_at": null
  },
  "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."
  ],
  "connected_context": {
    "meaning": "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.",
    "corpus_size": 297,
    "generated_at": "2026-07-31T10:07:27.765Z",
    "connections": [
      {
        "title": "How Kepler Built Verifiable AI for Financial Services — Vinoo Ganesh",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=Tt2kX2sgQio",
        "feed7_url": "https://feed7.dev/p/how-kepler-built-verifiable-ai-for-financial-services-vinoo-ganesh-0yqmhy7",
        "reason": "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."
      },
      {
        "title": "Build for the Memo, Not the Demo — Shawn Chan, China Resources Holdings",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=tJFjeMBKbIY",
        "feed7_url": "https://feed7.dev/p/build-for-the-memo-not-the-demo-shawn-chan-china-resources-holdings-0i3s3oo",
        "reason": "Claim-level provenance and explicit uncertainty become implementation requirements when outcome correlations may not justify causal recommendations."
      },
      {
        "title": "CausalForge: A Formally Grounded, Self-Improving Agentic Framework for Automated Research in Causal Inference",
        "source_name": "arXiv",
        "source_url": "https://arxiv.org/abs/2607.22511v1",
        "feed7_url": "https://feed7.dev/p/2607-22511v1-0mgsdh3",
        "reason": "Both distinguish valid derivation from valid interpretation: formal or statistical machinery cannot ensure that assumptions and claims match the intended real-world question."
      },
      {
        "title": "Semantic Blindness: 500,000 Sensors Confused an LLM - Raahul Singh & Vanč Levstik, Phaidra",
        "source_name": "YouTube",
        "source_url": "https://www.youtube.com/watch?v=EUsPvBeIx70",
        "feed7_url": "https://feed7.dev/p/semantic-blindness-500-000-sensors-confused-an-llm-raahul-singh-vanc-lev-159c4yr",
        "reason": "Both replace unconstrained model inference with structured, domain-specific resolution, but Intuit grounds actions in observed outcomes rather than deterministic entity lookup."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": "2026-07-29T20:00:06.000Z",
  "modified_at": "2026-07-29T20:00:06.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/why-off-the-shelf-ai-doesn-t-understand-money-udi-menkes-intuit-0y6w9rk",
    "json": "https://feed7.dev/p/why-off-the-shelf-ai-doesn-t-understand-money-udi-menkes-intuit-0y6w9rk.json",
    "markdown": "https://feed7.dev/p/why-off-the-shelf-ai-doesn-t-understand-money-udi-menkes-intuit-0y6w9rk.md"
  }
}