Instead of manually crafting complex evaluation prompts, a more effective workflow is for a human to define the high-level criteria and red flags. Then, feed this guidance into a powerful LLM to generate the final, detailed, and robust prompt for the evaluation system, as AI is often better at prompt construction.

Instead of waiting for AI models to be perfect, design your application from the start to allow for human correction. This pragmatic approach acknowledges AI's inherent uncertainty and allows you to deliver value sooner by leveraging human oversight to handle edge cases.

Don't ask an LLM to perform initial error analysis; it lacks the product context to spot subtle failures. Instead, have a human expert write detailed, freeform notes ("open codes"). Then, leverage an LLM's strength in synthesis to automatically categorize those hundreds of human-written notes into actionable failure themes ("axial codes").

AI evaluation shouldn't be confined to engineering silos. Subject matter experts (SMEs) and business users hold the critical domain knowledge to assess what's "good." Providing them with GUI-based tools, like an "eval studio," is crucial for continuous improvement and building trustworthy enterprise AI.

The common mistake in building AI evals is jumping straight to writing automated tests. The correct first step is a manual process called "error analysis" or "open coding," where a product expert reviews real user interaction logs to understand what's actually going wrong. This grounds your entire evaluation process in reality.

Assigning error analysis to engineers or external teams is a huge pitfall. The process of reviewing traces and identifying failures is where product taste, domain expertise, and unique user understanding are embedded into the AI. It is a core product management function, not a technical task to be delegated.

Because PMs deeply understand the customer's job, needs, and alternatives, they are the only ones qualified to write the evaluation criteria for what a successful AI output looks like. This critical task goes beyond technical metrics and is core to the PM's role in the AI era.

Do not blindly trust an LLM's evaluation scores. The biggest mistake is showing stakeholders metrics that don't match their perception of product quality. To build trust, first hand-label a sample of data with binary outcomes (good/bad), then compare the LLM judge's scores against these human labels to ensure agreement before deploying the eval.

A one-size-fits-all evaluation method is inefficient. Use simple code for deterministic checks like word count. Leverage an LLM-as-a-judge for subjective qualities like tone. Reserve costly human evaluation for ambiguous cases flagged by the LLM or for validating new features.