Every real run, newest first unless a column says otherwise. Open one to see the page the agent wrote, its violations and what each step cost.
Only runs of rule render/runtime-error (remove).
| Task | Model | Context | Design system | Quality | Done | Steps | Cost | When ↑ |
|---|---|---|---|---|---|---|---|---|
| kyc-form | nemotron-3.5-lightning-free | ds-mcp-check | 0 | 24 | Incomplete | 8 | $0.0000 | Nov 10, 11:13 |
58 runs match.
| stock-adjustment | nemotron-3.5-lightning-free | none | 18 | 9 | Incomplete | 3 | $0.0000 | Nov 10, 15:00 |
| goods-receipt | nemotron-3.5-lightning-free | ds-mcp | 6 | 12 | Incomplete | 10 | $0.0000 | Nov 10, 15:00 |
| pick-list | nemotron-3.5-lightning-free | ds-mcp | 5 | 9 | Incomplete | 4 | $0.0000 | Nov 10, 15:01 |
| shipment-detail | nemotron-3.5-lightning-free | ds-mcp | 8 | 27 | Incomplete | 7 | $0.0000 | Nov 10, 15:01 |
| stock-adjustment | nemotron-3.5-lightning-free | ds-mcp | 1 | 13 | Incomplete | 4 | $0.0000 | Nov 10, 15:02 |
| card-dispute | nemotron-3.5-lightning-free | none | 24 | 21 | Incomplete | 3 | $0.0000 | Nov 10, 15:57 |
| goods-receipt | nemotron-3.5-lightning-free | none | 10 | 11 | Incomplete | 3 | $0.0000 | Nov 10, 15:58 |