Don't treat evals as a mere checklist. Instead, use them as a creative tool to discover opportunities. A well-designed eval can reveal that a product is underperforming for a specific user segment, pointing directly to areas for high-impact improvement that a simple "vibe check" would miss.

Once AI coding agents reach a high performance level, objective benchmarks become less important than a developer's subjective experience. Like a warrior choosing a sword, the best tool is often the one that has the right "feel," writes code in a preferred style, and integrates seamlessly into a human workflow.

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").

Treating AI evaluation like a final exam is a mistake. For critical enterprise systems, evaluations should be embedded at every step of an agent's workflow (e.g., after planning, before action). This is akin to unit testing in classic software development and is essential for building trustworthy, production-ready agents.

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.

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.

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.

You don't need to create an automated "LLM as a judge" for every potential failure. Many issues discovered during error analysis can be fixed with a simple prompt adjustment. Reserve the effort of building robust, automated evals for the 4-7 most persistent and critical failure modes that prompt changes alone cannot solve.

Instead of seeking a "magical system" for AI quality, the most effective starting point is a manual process called error analysis. This involves spending a few hours reading through ~100 random user interactions, taking simple notes on failures, and then categorizing those notes to identify the most common problems.