While evals involve testing, their purpose isn't just to report bugs (information), like traditional QA. For an AI PM, evals are a core tool to actively shape and improve the product's behavior and performance (transformation) by iteratively refining prompts, models, and orchestration layers.

Building non-deterministic AI products fundamentally changes the PM role. Instead of creating detailed, rigid specifications, the PM's primary task becomes defining and codifying "what good looks like." This is done by repeatedly grading AI outputs to train evaluation systems and guide the model's behavior.

Descript evaluates its Underlord AI agent using a three-tier system: 'didn't break anything' (baseline), 'did what I asked' (functional), and 'did it well' (human-level quality). This framework pushes beyond mere task completion to assess true user satisfaction.

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.

Don't aim for a 100% accurate evaluation system. A good system reveals a 'healthy percentage' of incorrect outputs. Getting excited when evals are wrong is key, as each failure is a clear, actionable opportunity to improve your AI agent.

The prompts for your "LLM as a judge" evals function as a new form of PRD. They explicitly define the desired behavior, edge cases, and quality standards for your AI agent. Unlike static PRDs, these are living documents, derived from real user data and are constantly, automatically testing if the product meets its requirements.

Evals shift product development from defining the 'how' to defining the 'what'. By creating quantifiable tests and success criteria, evals act like a modern PRD. This allows an AI model to creatively figure out the implementation while the team focuses on defining the desired outcome through concrete examples.

When an AI agent performs poorly, the most effective solution isn't clever prompt engineering. Braintrust's CEO's strategy is to "close the session" and rewrite the evaluation script from scratch. This forces clarity on the definition of success, which is often the root cause of the agent's failure.