conceptEvaluación y Medición~1 min de lecturaActualizado 2026-06-07#evaluation#methodology#eval-driven#workflow
Esta nota todavía no está traducida, así que se muestra la fuente en inglés.

Eval-driven development

The defining methodology of serious AI engineering: build the eval first, then iterate against it. Because LLM systems are non-deterministic and "looks good" doesn't scale, an eval set is the only honest signal that a change helped. Evals are to AI what unit tests are to software.

Why "try it and see" fails

A single good output says nothing about the distribution of inputs. Tuning a prompt, swapping a model, or changing retrieval by eyeballing one example means you fix one case and silently break others. Without a measurement, "better" is a feeling.

The loop

  1. Collect real examples — from logs, users, and known failure cases.
  2. Define success — exact checks where possible, a rubric + LLM-as-judge where not, human review for the rest.
  3. Establish a baseline — score the current system.
  4. Change one thing, run the whole eval set, compare to baseline.
  5. Error-analyze the failures (systematically), which feeds the next change and new eval cases.
  6. Gate releases on the eval in CI — no regressions ship.

It compounds

Every production failure becomes a new eval case, so the suite keeps getting stricter as the system meets reality — the flywheel applied to quality. The eval set becomes your most valuable, hardest-to-copy asset.

Where it plugs into the stack

Eval-driven development is the practice; the targeted notes are the techniques: building eval sets, LLM-as-judge, regression testing, RAG eval, agent eval.

Pitfall

Building the product first and bolting on evals "later" — by then you have no baseline, no regression safety net, and changes are pure guesswork. Start the eval set on day one, even tiny; a 20-example eval beats zero by an enormous margin.

Connects to: designing eval sets · iterating prompts · the data flywheel