pvakati-tech.ai
// quality / evaluation

Evaluating LLM & Agent Systems

You can't improve what you don't measure — and you can't ship an agent you can't regression-test. This is how to evaluate LLM and agent systems: the methods, the metrics that matter, and treating evals as CI rather than a launch-day afterthought.

eval setsLLM-as-judgeonline metricsregression
Back to topics
// four_methods

Four ways to measure quality

Use them together — offline sets for regression, judges for scale, humans for ground truth, and online metrics for reality.

Offline eval sets

A fixed, versioned set of inputs with expected properties. Run it on every prompt, model, or retrieval change — the backbone of everything else.

LLM-as-judge

A model scores outputs against a rubric (faithfulness, helpfulness, tone). Cheap and scalable, but calibrate it against human labels and watch for bias.

Human review

Expert spot-checks on a sample, especially for regulated or high-risk actions. The ground truth that keeps automated judges honest.

Online metrics

Production signals: task success, override/edit rate, thumbs, latency, cost, escalation, and complaint rate — real behavior, not a lab.

// metrics_that_matter

What to track, by layer

Retrieval (RAG)

  • recall@k
  • MRR / nDCG
  • context precision

Generation

  • faithfulness / groundedness
  • answer relevance
  • toxicity / policy pass

Agents

  • task success rate
  • tool-call accuracy
  • steps to completion
  • override rate

Operations

  • p95 latency
  • cost per task
  • escalation rate
// the_eval_loop

Evals as CI, not a launch checklist

01

Curate an eval set

Real prompts + edge cases + past failures, each with expected properties or a rubric. Version it in the repo.

02

Score

Run automated judges + metrics on every change; sample a slice for human review.

03

Gate the release

Block deploys that regress on faithfulness, task success, or policy pass — evals are CI, not a one-off.

04

Watch production

Capture online metrics and thumbs; the worst cases feed straight back into the eval set.

Evaluation anti-patterns

Shipping on vibes — a good demo is not an eval.

Trusting an LLM judge you never calibrated against humans.

Evaluating generation while retrieval is silently broken.

A static eval set that never absorbs new production failures.

// references

Tools & further reading