> ## Documentation Index
> Fetch the complete documentation index at: https://docs.obversa.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Can an LLM Judge Replace a Person?

> It can fail a step and pick a winner; it cannot ship the change. A judge score is not an approval.

It can decide a step; it should not decide the ship. In Obversa a model
can review another model's work and fail it, and a judge can score
several candidates and pick one. Neither is an approval. The tournament's
judge in the shipped example is a function that reads the files on disk,
not a model, and a review seat can be a model from another family. Obversa
does not calibrate an LLM judge or run a benchmark, and a high score clears
a gate without proving the work is right.

## In Obversa

The judge scores what is on disk, and a candidate that failed its test
scores nothing:

```ts examples/tournament.ts (excerpt) {2-3} theme={null}
const score = async (outcome: Outcome, ctx: JobContext): Promise<number> => {
  if (outcome.status !== 'pass') return 0;
  const source = await readFile(join(ctx.workspace.dir, 'src/retry.ts'), 'utf8');
  let points = 1;
  if (/MAX_ATTEMPTS\s*=\s*\d+/.test(source)) points += 1;
  if (/signal\?\.aborted/.test(source)) points += 1;
  return points;
};
```

The highest score lands and the rest leave nothing behind. Put a test or a
person behind the gates that matter most.

## Human approval

The last word belongs to a person as a step, not to a score. [Where does a
person approve the change?](/glossary/human-approval) says how that step
works.

## Next steps

* [Three candidates, one winner](/patterns/tournament): the judge with a real run.
* [Evals in an agent workflow](/reviewing/evals): every kind of check that decides the next step.