Skip to main content

Changelog

Follow new updates and improvements to beval.

Fresh look across the board

We've given the entire app a visual refresh — every card, detail page, and table has been redesigned for consistency and clarity.

  • Redesigned cards — Dataset, eval, and ground truth cards now share a clean portrait layout with icons, metadata rows, and separators. Dataset cards show which evals are attached. Eval cards show when they were last run.
  • New runs table — Runs are now displayed in a proper sortable table with filters for eval, column, status, dataset, and date range. Click any row to see the full results.
  • Cleaner detail pages — Eval and dataset detail pages use flat section headers instead of nested cards, giving everything more breathing room.
  • Eval descriptions — Evals now have an optional description field so you can capture the intent behind each eval in plain language.
  • Daily rate limit — To keep things fair, there's now a limit of 200 trace evaluations per day per user. You'll see a clear message if you hit it.
NewImproved

Cleaner UI, better example dataset

A round of polish across the app:

  • Separated footer buttons — dialogs, alert confirmations, and the login/signup forms now have a visually distinct footer area with a subtle border and background, matching modern shadcn conventions.

  • Decluttered layouts — removed unnecessary card wrappers from the eval prompt, eval runs section, danger zone, and accuracy metrics. Pages feel lighter and less boxy.

  • Ground truth page tidied up — consolidated the labelling page from 6 separate cards into 3 clean sections. Navigation is now integrated into the trace card, and all sidebar controls live in a single panel.

  • Richer example dataset — the example dataset now includes 10 trip planning conversations (up from 3) covering diverse scenarios like solo backpacking, family holidays, ski trips, and more. It also ships with 3 example evals (boolean, score, and category) so new users can see the full range of eval types immediately.

  • Component showcase — added a hidden page at /app/components showing all UI components used across the app. Handy as a living style guide.

NewImproved

Ground truth labelling, redesigned evals toolkit, and faster navigation

Ground truth labelling

You can now manually label traces to measure how accurate your LLM evals are. For boolean, score, and category evals attached to a dataset, go to the new Ground Truth page in the sidebar to start labelling. Once you have labels, Beval calculates precision, recall, F1, and accuracy automatically.

After viewing run results, you'll also see a prompt to start labelling right there — so you can go from "are these results right?" to measuring accuracy in one click.

Evals toolkit

The Evals page has been redesigned as a toolkit grouped by type — Boolean, Score, Category, and Comment. Each section explains what the eval type does and has a quick "+ New" card to create one. A search bar at the top lets you filter across all types.

Runs now show eval version

The Runs table now displays which version of the eval was used for each run, making it easier to track prompt iterations.

Faster page navigation

Every page now has loading skeletons so navigating between views feels snappier — no more blank screens while data loads.

Datasets page refresh

The Datasets page now has a search bar and groups your datasets by Today, This week, and Earlier for easier browsing.

NewImproved

Earlier updates