Before building an AI agent, product managers must first create an evaluation set and scorecard. This 'eval-driven development' approach is critical for measuring whether training is improving the model and aligning its progress with the product vision. Without it, you cannot objectively demonstrate progress.

Pre-training on internet text data is hitting a wall. The next major advancements will come from reinforcement learning (RL), where models learn by interacting with simulated environments (like games or fake e-commerce sites). This post-training phase is in its infancy but will soon consume the majority of compute.

Instead of manually refining a complex prompt, create a process where an AI agent evaluates its own output. By providing a framework for self-critique, including quantitative scores and qualitative reasoning, the AI can iteratively enhance its own system instructions and achieve a much stronger result.

Reinforcement Learning with Human Feedback (RLHF) is a popular term, but it's just one method. The core concept is reinforcing desired model behavior using various signals. These can include AI feedback (RLAIF), where another AI judges the output, or verifiable rewards, like checking if a model's answer to a math problem is correct.

The primary bottleneck in improving AI is no longer data or compute, but the creation of 'evals'—tests that measure a model's capabilities. These evals act as product requirement documents (PRDs) for researchers, defining what success looks like and guiding the training process.

Building a functional AI agent is just the starting point. The real work lies in developing a set of evaluations ("evals") to test if the agent consistently behaves as expected. Without quantifying failures and successes against a standard, you're just guessing, not iteratively improving the agent's performance.

Unlike pre-training's simpler data pipeline, RL involves many "moving parts" because each task can have a unique grading setup and infrastructure. This complexity, not just the algorithm itself, is the primary challenge for researchers managing live training runs at scale.

The distinction between imitation learning and reinforcement learning (RL) is not a rigid dichotomy. Next-token prediction in LLMs can be framed as a form of RL where the "episode" is just one token long and the reward is based on prediction accuracy. This conceptual model places both learning paradigms on a continuous spectrum rather than in separate categories.

The 'environment' concept extends beyond RL. It's a universal framework for any model interaction, encompassing the task, the harness, and the rubric. This same structure can be used for evaluations, A/B testing, prompt optimization, and synthetic data generation, making it a core building block for AI development.