The stock of one warehouse: on hand, reserved and available for each item, with the ones at or below their reorder point marked.
What the agent reads, word for word.
Build the stock page of one warehouse.
At the top, show the warehouse name and when the stock was last counted, then two numbers: how many items the warehouse holds, and how many of them need reordering.
Below, list every item with its SKU, name, location, quantity on hand, quantity reserved for open orders, and quantity "Available" (on hand minus reserved), with its unit. An item needs reordering when its quantity on hand is at or below its reorder point: mark those items "Reorder" so the team sees them at a glance.
The data is in `./fixture.json`.
The page must show these texts, or the run is not done. A good answer uses these components.
By design-system violations.
| Run | Design system | Cost |
|---|---|---|
| nemotron-3.5-lightning-free at genui-spec-domain | 0 | $0.0000 |
| beam-free at genui-spec-domain | 0 | $0.0000 |
| beam-free at genui-spec | 0 | $0.0000 |
Mean design-system violations per run on this task.
| Context | Mean | nemotron-3.5-lightning-free | beam-free |
|---|---|---|---|
| none File tools only | 18.5 | 3.5 | 33.5 |
| ds-mcp Our design-system MCP | 0 |
Written by hand, graded with zero violations, rendered by the browser check in every build. The agent never sees it.
import { Badge, Card, CardBody, CardDescription, CardHeader, CardTitle, Grid, Stat, Table, TableBody, TableCell,| Run | Design system | Cost |
|---|
| beam-free at none | 48 | $0.0000 |
| beam-free at none | 19 | $0.0000 |
| nemotron-3.5-lightning-free at none | 7 | $0.0000 |
| 0 |
| 0 |
| ds-mcp-check-full A checker with compiler and linter | 0 | 0 | 0 |
| genui-spec A view from the catalog, six tasks | 0 | 0 | 0 |
| genui-spec-domain A view with the product's own components | 0 | 0 | 0 |