Row Evaluation
ExamplesRow evaluation with bounded concurrency, cancellation, stale results after editing, and review filtering with mock and authenticated live Jev modes, saved results, and detailed distributions.
Evaluate selected rows, switch local rule providers and criteria, and recover from simulated rate limits, timeouts, save failures and cancellation without AI calls.
Change the width and theme, then interact with the components.
Evaluation studio
Compare evaluation rules and rehearse recovery, without API calls or durable storage.
Attempts: 0 · Completed: 0/3
Simulated saved snapshots: 0
Provider and length changes invalidate old results. Editing during evaluation must not apply a late result. Real 429 responses require server backoff; real save failures require reading history before retrying paid work.
bun add @reopt-ai/opt-datagridimport { DataGrid, type DataGridColumn } from "@reopt-ai/opt-datagrid";
import { useDataGridRowEvaluation } from "@reopt-ai/opt-datagrid/evaluation";Row evaluation with bounded concurrency, cancellation, stale results after editing, and review filtering with mock and authenticated live Jev modes, saved results, and detailed distributions.
A table a real model writes while you watch: YAML becomes patches, changes wait for review, edits are never overwritten, and formulas, sorting and per-row AI columns take one line.
Starter spreadsheet grid with editable columns and commit feedback.