# Your Company Should Train Its Own AI Models - Will Brown, Prime Intellect

## Executive summary

The talk argues that for an organization to become truly AI-native, it must move beyond simply using agents and instead build infrastructure to train models on its unique, unwritten institutional knowledge. The core challenge is that agents relearn everything because proprietary workflows and decisions are not codified. The solution involves creating self-improving loops by treating model training like a software development lifecycle, utilizing mechanisms like 'Evals as test cases,' 'Decision Models,' and 'widget-style interfaces' to capture human preference and latent knowledge for durable, weight-based learning.

## Key takeaways

- The Problem of Latent Knowledge: Organizations possess vast amounts of implicit knowledge (preferences, friction points, heuristics) that are not written down in code or documents. This latent knowledge is critical for optimal AI performance but is lost when agents operate without continuous, domain-specific training.
- The Need for Durable Learning: Relying solely on in-context learning (prompting) is inefficient because agents must reprocess massive amounts of input tokens for every workflow, leading to high costs and poor performance compared to models trained on proprietary data.
- Key Training Mechanisms: To achieve durable learning, organizations should implement 'Evals as test cases' (treating the model like a codebase with test cycles), 'Decision Models' (learning human judgment in specific scenarios), and 'widget-style interfaces' (allowing direct human feedback to act as a label).
- The Self-Improving Loop: The goal is to create a continuous, self-improvement loop where daily agent usage generates traces and feedback, which are then used in nightly training runs to compound institutional knowledge into the model's weights.

## Technical details

- AI-Native Organization Definition: An AI-native organization involves the deep integration of agents throughout the entire life cycle of the company, moving beyond simple cloud-based agent deployments.
- Model Training Pipeline: The process involves collecting traces (prompts and model outputs), creating 'Evals' (evaluations/test cases) from these traces, and using specialized tooling to refine these into robust training environments that are blended real and synthetic.
- Decision Models and Routing: These models are valuable because they capture human judgment in specific, labelable actions (e.g., approving tool calls). They allow systems to learn when to use a cheaper model versus a larger, more expensive one, optimizing cost and performance.
- Human-in-the-Loop Interfaces: Widget-style interfaces provide a highly ergonomic way for humans to give direct feedback (a 'signal') to the model, acting as a direct label that improves the model's weights and avoids issues like reward hacking.
- Investment Scale Example: The speaker cited an example of a model trained for knowledge work (spreadsheets/slides) that represented an employee-scale investment of approximately $300K.

## Practical implications

- For build engineers, the focus shifts from merely deploying agents to building the 'orchestration layer' that manages the continuous data flow (traces -> evals -> training runs).
- Implementing a structured feedback loop (human-in-the-loop) that automatically captures human preferences and decisions is critical for achieving durable, compounding knowledge.
- Treating the model itself as a codebase that requires continuous testing (Evals) and version control is the most practical approach for enterprise adoption.

## Topics

AI Infrastructure, Continual Learning, Agent Orchestration, Enterprise AI, Machine Learning Operations (MLOps), Will Brown, Prime Intellect, AIE CODE summit

Source: https://www.youtube.com/watch?v=5SRjPT2Eo7A