As you manage a fleet of agents, you cannot manually review every output. Platforms like HyperAgent use "Rubrics"—an evaluation framework where one LLM judges another's work against predefined criteria. This automates quality control, which is essential for scaling an agent-first business.

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.

The key to enabling an AI agent like Ralph to work autonomously isn't just a clever prompt, but a self-contained feedback loop. By providing clear, machine-verifiable "acceptance criteria" for each task, the agent can test its own work and confirm completion without requiring human intervention or subjective feedback.

Building reliable AI agents requires a developer mindset shift. The most critical task is not writing the agent's code but creating robust evaluations ('evals') that define and verify the desired business outcome. This makes a test-driven development approach non-negotiable for enterprise AI.

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.

The frontier of AI training is moving beyond humans ranking model outputs (RLHF). Now, high-skilled experts create detailed success criteria (like rubrics or unit tests), which an AI then uses to provide feedback to the main model at scale, a process called RLAIF.

Effectively using AI for a complex coding project required creating a spec-driven test framework. This provided the AI agent a 'fixed point' (passing tests) to iterate towards, enabling it to self-correct and autonomously verify the correctness of its output in a successful feedback loop.

Data that measures success, like a grading rubric, is far more valuable for AI training than simple raw output. This 'second kind of data' enables iterative learning by allowing models to attempt a problem, receive a score, and learn from the feedback.

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.