Skip to content
Agentic UI Kit
Buy

Agent OPS Evals

Eval runs comparing two prompt versions and models with score charts and a results matrix.

Full screen Try a theme

Choose the primitives library your project already uses. Both look the same: your theme, not the variant, controls colors, shape, type and motion.

About this page

What it's for

  • Eval runs comparing two prompt versions and models with score charts and a results matrix.
  • Evaluation dashboard where a new run is started on a dataset and compared with the previous one.

Includes

  • Eval runs list
  • New run dialog
  • Run progress
  • Failed run retry
  • Baseline vs candidate chart
  • Score histogram
  • Results matrix
  • Case detail dialog

Works with

  • Radix UI and Base UI primitives (pick the one your project uses)
  • React 19 and Tailwind CSS 4 in Next.js (App Router), Vite, React Router or TanStack Start, installed with the agentic-ui or shadcn CLI
  • Your theme tokens, in light and dark mode
  • 1 template or blueprint on this site use it (below)

Install

Included with Agentic UI Kit (one-time license). Install needs your license key: see pricing · connect your project.

Agentic UI CLI
agentic-ui add agent-ops-evals
Installs through shadcn and adapts the component to your design tokens.
shadcn CLI
npx shadcn@4.17.0 add @agentic-ui/agent-ops-evals

Used in

Type
Page
Variants
Radix UI and Base UI
Themes
Light and dark
Widths
Preview it at desktop, tablet and mobile widths above.
Motion
Animated, with a reduced-motion fallback
Sample data
Ships with sample data in models.ts, seed.ts, prompts.ts, world-plan.ts, people.ts, prompt-texts.ts, evals.ts, datasets.ts, world.ts, span-kit.ts, span-flows.ts, content.ts; replace it with your own.