AI Engineer

Your Company Has No Model of Itself. Agents Can Build One - Joao Wenzel, Citadel Securities

Published 2026-11-08 · Duration 18:56

Summary

The video proposes building an 'institutional memory layer'—a world model for a company—using an agentic system that moves beyond simple Retrieval-Augmented Generation (RAG). This system approximates the knowledge of a single, omniscient employee by synthesizing evidence from disparate sources (e.g., decks, Slack, PRs, meeting notes). Drawing inspiration from robotics, the model functions as a state estimator, continuously updating its beliefs by incorporating new evidence, allowing facts to age, grading predictions against outcomes, and accepting human corrections. This approach helps identify critical project risks, such as 'watermelon projects' (green on the outside, red on the inside).

Download summary

Key takeaways

  1. The World Model as a State Estimator 5:05

    The system must treat corporate knowledge not as a static database, but as a dynamic state estimator. This means tracking how long a fact has been observed (half-life) and how that signal is corroborated by other sources.

  2. The Core Agentic Loop 10:11

    Effective knowledge capture requires a continuous loop: Update (incorporating new evidence), Age (applying recency bias to facts), Observe (using specialist agents instead of a single pass), Grade (back-testing predictions against actual outcomes), and Correct (allowing human feedback to steer the system).

  3. Bottom-Up vs. Top-Down Evidence

    While top-down sources (decks, status reports) are clean but prone to human bias, bottom-up sources (Slack, PRs, agent traces) are noisy but contain high signal, requiring synthesis to build a complete picture.

More digests on Agentic Systems

Technical details

  • Data Synthesis and Evidence Sources

    The system must integrate multiple data types: formal documents (decks, strategy docs), communication logs (Slack, meeting notes), code changes (PRs), and detailed user/agent traces. The synthesis of these disparate sources is key to building the 'institutional memory layer.'

  • State Estimation Principles 912s

    The system must manage belief decay: the less frequently a fact is observed, the less trustworthy it becomes. This requires establishing a longitudinal, traceable audit layer for all claims.

  • Specialized Agent Workflows 1012s

    Instead of relying on a single large model pass (YOLO method), the system should use a series of specialist agents to break down collateral and look for specific details, significantly improving the quality of updates.

  • Predictive Capabilities (Grading) 1112s

    By establishing historical snapshots (e.g., as of February), the agent can back-test its predictions, showing that flagged statuses (green but flagged) were twice as likely to slip or change color (yellow/red) than those left unflagged.

Mentioned resources

Channel & topics

Watch on YouTube · Back to latest

This independent, AI-assisted summary is provided for commentary and informational purposes. It may contain errors or omit important context. Please watch the original video for the creator's complete presentation. Video, thumbnail, and related copyrights belong to their respective owners.