Eval Library
L
For LovableCode AssistantAi Platform

Deployment And Hosting

Lovable · Lovable

AI App Builder — Lovable

Lovable evals — Deployment & Hosting (relift v3 InfraRed)

About Lovable

Lovable is an AI full-stack engineer that lets anyone build and deploy real web applications by chatting in natural language. Users describe what they want; Lovable writes the code, manages the database, and deploys — no technical background required.

Employees

~30

Industry

AI App Builder

Headquarters

Stockholm, Sweden

Sample tests· showing 3 of 9

#InputExpected behaviorCheck
01

Scaffold finished. User wants the preview URL to share.

Deploy the build to <slug>.lovable.app, surface the URL in chat and the project dashboard. The URL should serve the just-built artifact (not a stale or empty page) and be reachable from any browser without login.

Pass / FailAi Platformhigh
02

Latest build introduced a runtime regression. User clicks 'rollback.'

Restore the previous deployed build artifact to the preview URL within the documented rollback path, keep the source tree untouched (or revert + commit on a branch if source rollback is desired), and confirm the artifact serving the URL.

Pass / FailAi Platformcritical
03

Generated SPA needs a not-found page. Vite/React-Router or Next.js app router.

Add a documented catch-all route (App Router not-found.tsx for Next.js; a Route path='*' fallback for React Router) that renders a 404 page with a link home. Verify the route serves a 404 status code (Next.js) where applicable.

Pass / FailAi Platformmedium

How this eval is graded

Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.

Rubric criteria

  • Lovable
  • Ai Platform
  • Deployment And Hosting

Recommended for

LovableLovable customers

Works with

Related evals

Run this eval in your workspace

Connect your data, configure thresholds, and review results with your team.