# Eval scorecard

Show how an agent version did on a fixed suite, against the baseline, with what to look at first.

For: The people who build and release the agent.

Web page: https://candor.themethodic.com/screens/eval-scorecard

## Layouts

### Scorecard against a baseline

Pick it when: The default: one run against the one before it.

Layout: An overall rate, then each criterion's rate and its change from the baseline, over failure clusters.

Items:

- **Eval scorecard** (`eval-scorecard`, Pro; https://candor.themethodic.com/docs/eval-scorecard.md): An eval run against its baseline: the overall pass rate, then each criterion with its change.
- **Failure clusters** (`failure-clusters`, Pro; https://candor.themethodic.com/docs/failure-clusters.md): Failing runs grouped by what went wrong, largest first.
- **Stat card** (`stat-card`, Pro; https://candor.themethodic.com/docs/stat-card.md): One metric with its change against a named period.

```bash
npx candor-ui add eval-scorecard failure-clusters stat-card
```

### Two runs side by side

Pick it when: Deciding between two versions or two models.

Layout: Two columns of measures with the change between them.

Items:

- **Comparison view** (`comparison-view`, Pro; https://candor.themethodic.com/docs/comparison-view.md): Before and after, numerically, coloured by whether the change is good.
- **Subscore card** (`subscore-card`, Pro; https://candor.themethodic.com/docs/subscore-card.md): Weighted subscores behind an overall score.
- **Eval scorecard** (`eval-scorecard`, Pro; https://candor.themethodic.com/docs/eval-scorecard.md): Each side's scorecard.

```bash
npx candor-ui add comparison-view subscore-card eval-scorecard
```

### Quality over time

Pick it when: Watching a live agent drift or recover after a change.

Layout: A line-like column chart of scores with markers for what changed alongside.

Items:

- **Quality trend** (`quality-trend`, Pro; https://candor.themethodic.com/docs/quality-trend.md): Scores over time with what changed alongside: a model switch, an instruction edit.
- **Version history** (`version-history`, Pro; https://candor.themethodic.com/docs/version-history.md): Which version was live when.

```bash
npx candor-ui add quality-trend version-history
```

## Rules that matter most here

- **Unknown stays unknown** (https://candor.themethodic.com/principles#unknown-stays-unknown): A criterion with too few cases shows its count and no rate; a missing baseline is "no baseline".
- **Motion never says something false** (https://candor.themethodic.com/principles#motion-follows-the-outcome): A change is coloured good or bad only by what it is, and a flat change isn't coloured.
- **Reasoning is believed, not verified** (https://candor.themethodic.com/principles#reasoning-is-believed): A judge's reasons are shown as the judge's, not as verified.

A full-stack block builds this with an agent route and a store: `eval-dashboard` (https://candor.themethodic.com/docs/eval-dashboard.md). Each block has a `-claude` twin for the Claude Agent SDK.

## Brief for a coding agent

Paste this to the agent that builds the screen.

```text
Build an eval scorecard with Candor UI. Start from the eval-dashboard block (eval-dashboard-claude for the Claude Agent SDK): each version of an agent runs a fixed suite of cases checked in code, and a page compares the runs.
EvalScorecard shows the overall pass rate and each criterion's rate and change from the baseline; FailureClusters groups the failures by what went wrong, largest first.
Show counts next to rates. A criterion with too few cases shows its count and no rate; no baseline says "no baseline".
ComparisonView puts two runs side by side; colour a change only when it is good or bad.
QualityTrend shows scores over time with what changed alongside.
Pass scores as plain data; Candor does not run the evals.

Start from the "Scorecard against a baseline" layout: An overall rate, then each criterion's rate and its change from the baseline, over failure clusters.
Candor items: eval-scorecard (https://candor.themethodic.com/docs/eval-scorecard.md), failure-clusters (https://candor.themethodic.com/docs/failure-clusters.md), stat-card (https://candor.themethodic.com/docs/stat-card.md).
Install: npx candor-ui add eval-scorecard failure-clusters stat-card
Read each item's docs before using it and take its props from there; don't guess them. Pro and Premium items need the person's licence key, which they add with `npx candor-ui key <key>`; don't ask for it.
```