Agent Benchmark
Design-agent benchmark runs, scenario authoring, suites, reports, history, and regression review.
- Benchmark runs
- Scenarios
- Suites
- Reports
- Regression history
One entry point for catalog ingestion, catalog debugging, scan review, and image generation evaluation workflows while the legacy tools are migrated into this application.
Design-agent benchmark runs, scenario authoring, suites, reports, history, and regression review.
Product ingestion, deployment review, model backfill, and Lowes catalog operations.
Debug viewer for catalog products, variants, imagery, and 3D model inspection.
Scan accuracy, grading, reports, review controls, and scan configuration.
Image generation evaluations, prompt tooling, strategies, executions, analytics, and review results.