Skip to content

How Lovable’s scores are calculated

The full audit trail, recomputed from the verdict data at build time through the same code that produced the leaderboard: verdict × quality × story weight per cell, cells sum to dimension scores, dimensions blend into the PA Score. Every number on the product page is reproducible from this page alone; for why the formula looks like this, see the methodology.

verdict factors: full ×1.0 · partial ×0.6 · disputed ×0.3 · none ×0.0 · n/a excluded from both sides · cell points = weight × quality × factor · cell max = weight × 10

PA Score27/100

Agent-ready 46.9 × 0.30 = 14.07

API quality 4.8 × 0.20 = 0.96

Openness 21.0 × 0.20 = 4.20

Built-in AI 46.7 × 0.15 = 7.00

Automation 6.0 × 0.15 = 0.90

(14.07 + 0.96 + 4.20 + 7.00 + 0.90) ÷ (0.30 + 0.20 + 0.20 + 0.15 + 0.15) = 27.13 ÷ 1.00 = 27.1

Scores are stored to 1 decimal; the product page’s pills round to whole numbers for display. Each dimension below shows the stories, verdicts, and cited evidence behind its number.

Agent-ready46.9/100×0.30 of the PA blend

Outside-in: can YOUR agent reach and drive this product — API, MCP, CLI, headless runs, agent docs.

Point an agent at llms.txt or agent-oriented docsweight 2

2 (weight) × 9 (quality) × 1.0 (full) = 18.0 of 20 max

  • [probe] https://docs.lovable.dev/llms.txtPROBE llms.txt: HTTP 200 at https://docs.lovable.dev/llms.txt # Lovable Documentation > Lovable Documentation — Build full-stack websites with AI using natural language. Explore Lov
  • [claimed-docs] https://docs.lovable.dev/integrations/lovable-mcp-server.mdyour AI agent can create projects, send messages to Lovable, inspect code, deploy apps, and more, all without leaving the client you're already working in
  • [claimed-docs] https://docs.lovable.dev/integrations/custom-mcp.mdLovable can read from it as live context while you build: internal CRMs, private APIs, company knowledge bases, or niche third-party tools.

Run the product headlessly / in CI for automationweight 2

2 (weight) × 3 (quality) × 0.6 (partial) = 3.6 of 20 max

  • [claimed-docs] https://docs.lovable.dev/integrations/lovable-mcp-server.mdyour AI agent can create projects, send messages to Lovable, inspect code, deploy apps, and more, all without leaving the client you're already working in
  • [claimed-docs] https://docs.lovable.dev/integrations/build-with-url.mdThe Lovable API Build with URL feature lets you create links that open Lovable with a prompt already written, and optionally with reference images and web pages attached.
  • [claimed-docs] https://docs.lovable.dev/features/agent-integrations.mdTurn a published Lovable app into an MCP server for ChatGPT, Claude, and other AI assistants. Configure tools, sign-in, permissions, and access.

Plug MCP servers into this product so it can use their toolsweight 3

3 (weight) × 8 (quality) × 1.0 (full) = 24.0 of 30 max

  • [claimed-docs] https://docs.lovable.dev/integrations/custom-mcp.mdLovable can read from it as live context while you build: internal CRMs, private APIs, company knowledge bases, or niche third-party tools.
  • [claimed-docs] https://docs.lovable.dev/integrations/mcp-registries.mdmembers then pick servers from it and connect them as chat connectors in a couple of clicks, instead of finding and pasting each server's URL by hand
  • [claimed-docs] https://docs.lovable.dev/integrations/clickhouse.mdthe ClickHouse app + chat connector lets your Lovable app run SQL queries against your ClickHouse database over the HTTP interface
  • [claimed-docs] https://docs.lovable.dev/integrations/desktop-app.mdYou get everything in the web app plus local MCP server support, multi-project tabs, and keyboard shortcuts.

Connect an agent via an official MCP serverweight 3

3 (weight) × 8 (quality) × 1.0 (full) = 24.0 of 30 max

  • [claimed-docs] https://docs.lovable.dev/integrations/lovable-mcp-server.mdyour AI agent can create projects, send messages to Lovable, inspect code, deploy apps, and more, all without leaving the client you're already working in
  • [claimed-docs] https://docs.lovable.dev/integrations/desktop-app.mdYou get everything in the web app plus local MCP server support, multi-project tabs, and keyboard shortcuts.
  • [claimed-docs] https://docs.lovable.dev/features/agent-integrations.mdTurn a published Lovable app into an MCP server for ChatGPT, Claude, and other AI assistants. Configure tools, sign-in, permissions, and access.
  • [claimed-docs] https://docs.lovable.dev/features/agent-integrations.mdTurn a published Lovable app into an MCP server for ChatGPT, Claude, and other AI assistants.

Use an official CLIweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Drive the product through a documented public APIweight 3

3 (weight) × 8 (quality) × 1.0 (full) = 24.0 of 30 max

  • [claimed-docs] https://docs.lovable.dev/integrations/lovable-mcp-server.mdyour AI agent can create projects, send messages to Lovable, inspect code, deploy apps, and more, all without leaving the client you're already working in
  • [claimed-docs] https://docs.lovable.dev/integrations/build-with-url.mdThe Lovable API Build with URL feature lets you create links that open Lovable with a prompt already written, and optionally with reference images and web pages attached.
  • [probe] https://docs.lovable.dev/openapi.jsonPROBE openapi: all candidate paths 404 (https://docs.lovable.dev/openapi.json, https://docs.lovable.dev/swagger.json, https://docs.lovable.dev/api/openapi.json, https://docs.lovable.dev/.well-known/openapi.json)

Issue scoped/least-privilege API credentials for an agentweight 2

2 (weight) × 4 (quality) × 0.6 (partial) = 4.8 of 20 max

  • [claimed-docs] https://docs.lovable.dev/features/agent-integrations.mdTurn a published Lovable app into an MCP server for ChatGPT, Claude, and other AI assistants. Configure tools, sign-in, permissions, and access.
  • [claimed-docs] https://docs.lovable.dev/features/agent-integrations.mdTurn a published Lovable app into an MCP server for ChatGPT, Claude, and other AI assistants.
  • [claimed-docs] https://docs.lovable.dev/introduction/lovable-for-enterprise.mdcentralized identity, granular access controls, workspace-wide security oversight, scheduled Deep scans, audit logs, regional code hosting

Build against official SDKsweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [claimed-docs] https://docs.lovable.dev/integrations/build-with-url.mdThe Lovable API Build with URL feature lets you create links that open Lovable with a prompt already written, and optionally with reference images and web pages attached.
  • [claimed-docs] https://docs.lovable.dev/integrations/lovable-mcp-server.mdyour AI agent can create projects, send messages to Lovable, inspect code, deploy apps, and more, all without leaving the client you're already working in
  • [probe] https://docs.lovable.dev/openapi.jsonPROBE openapi: all candidate paths 404 (https://docs.lovable.dev/openapi.json, https://docs.lovable.dev/swagger.json, https://docs.lovable.dev/api/openapi.json, https://docs.lovable.dev/.well-known/openapi.json)

Subscribe to events via webhooksweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Agent-ready = 98.4 ÷ 210 × 100 = 46.9

API quality4.8/100×0.20 of the PA blend

The programmable surface once an agent is there — machine-readable spec, interactive docs, sandbox, versioning discipline.

Explore an interactive API reference with runnable examplesweight 2

n/a — not applicable to this product: excluded from numerator and denominator

  • [probe] https://docs.lovable.dev/openapi.jsonPROBE openapi: all candidate paths 404 (https://docs.lovable.dev/openapi.json, https://docs.lovable.dev/swagger.json, https://docs.lovable.dev/api/openapi.json, https://docs.lovable.dev/.well-known/openapi.json)

Download a machine-readable API spec (OpenAPI or equivalent)weight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [probe] https://docs.lovable.dev/openapi.jsonPROBE openapi: all candidate paths 404 (https://docs.lovable.dev/openapi.json, https://docs.lovable.dev/swagger.json, https://docs.lovable.dev/api/openapi.json, https://docs.lovable.dev/.well-known/openapi.json)

Test against a sandbox environment without touching production dataweight 1

1 (weight) × 4 (quality) × 0.6 (partial) = 2.4 of 10 max

  • [claimed-docs] https://docs.lovable.dev/integrations/github.mdyou can export and sync your project to GitHub: back up your code, review changes in pull requests, work locally in your IDE, test features on branches, and deploy outside Lovable
  • [claimed-docs] https://docs.lovable.dev/integrations/github.mdback up your code, review changes in pull requests, work locally in your IDE, test features on branches, and deploy outside Lovable
  • [claimed-docs] https://docs.lovable.dev/features/collaboration.mdWhen several people build in the same project, each of you can work in your own draft: a separate copy of the project with its own chat and preview.
  • [claimed-docs] https://docs.lovable.dev/features/cloud.mdLovable hosts your app and includes a built-in backend (Cloud) with database, authentication, storage, edge functions, and AI, no infrastructure setup required.

Rely on versioned APIs with a documented deprecation policyweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [probe] https://docs.lovable.dev/openapi.jsonPROBE openapi: all candidate paths 404 (https://docs.lovable.dev/openapi.json, https://docs.lovable.dev/swagger.json, https://docs.lovable.dev/api/openapi.json, https://docs.lovable.dev/.well-known/openapi.json)
  • [claimed-docs] https://docs.lovable.dev/integrations/build-with-url.mdThe Lovable API Build with URL feature lets you create links that open Lovable with a prompt already written, and optionally with reference images and web pages attached.

API quality = 2.4 ÷ 50 × 100 = 4.8

Openness21.0/100×0.20 of the PA blend

Can you leave, inspect, or self-host — data export, open source, portability.

Do everything through the API that I can do in the UIweight 2

2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max

  • [claimed-docs] https://docs.lovable.dev/integrations/lovable-mcp-server.mdyour AI agent can create projects, send messages to Lovable, inspect code, deploy apps, and more, all without leaving the client you're already working in
  • [claimed-docs] https://docs.lovable.dev/integrations/build-with-url.mdThe Lovable API Build with URL feature lets you create links that open Lovable with a prompt already written, and optionally with reference images and web pages attached.
  • [probe] https://docs.lovable.dev/openapi.jsonPROBE openapi: all candidate paths 404 (https://docs.lovable.dev/openapi.json, https://docs.lovable.dev/swagger.json, https://docs.lovable.dev/api/openapi.json, https://docs.lovable.dev/.well-known/openapi.json)

Export all of my data in open formats and leaveweight 3

3 (weight) × 6 (quality) × 0.6 (partial) = 10.8 of 30 max

  • [claimed-docs] https://docs.lovable.dev/integrations/git-sync-overview.mdWork locally in your IDE. Clone the repository, edit and commit locally, and push. Your changes sync back into Lovable.
  • [claimed-docs] https://docs.lovable.dev/integrations/github.mdIf you only need a copy of your code, you can download your code directly from Lovable: use the Download codebase section in Project settings → Git
  • [claimed-docs] https://docs.lovable.dev/integrations/github.mdyou can export and sync your project to GitHub: back up your code, review changes in pull requests, work locally in your IDE, test features on branches, and deploy outside Lovable
  • [claimed-docs] https://docs.lovable.dev/integrations/github.mdback up your code, review changes in pull requests, work locally in your IDE, test features on branches, and deploy outside Lovable
  • [claimed-docs] https://docs.lovable.dev/integrations/git-sync-overview.mdGit sync connects a Lovable project to a repository you own on GitHub or GitLab, and keeps the two in sync automatically
  • [claimed-docs] https://docs.lovable.dev/features/database.mdFor direct database access, use the SQL editor at **Cloud tab → SQL editor**
  • [claimed-docs] https://docs.lovable.dev/features/cloud.mdThe built-in backend utilizes Supabase's open-source foundation, which means you get a production-ready environment from day one, without needing to set up Supabase separately

Read the product's source under an open licenseweight 2

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Self-host the core productweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

  • [claimed-docs] https://docs.lovable.dev/features/cloud.mdLovable hosts your app and includes a built-in backend (Cloud) with database, authentication, storage, edge functions, and AI, no infrastructure setup required.
  • [claimed-docs] https://docs.lovable.dev/features/cloud.mdLovable hosts your app and includes a built-in backend (Cloud) with a database, storage, authentication, realtime, and functions.
  • [claimed-docs] https://docs.lovable.dev/introduction/getting-started.mdBuild your first app and put it live on the web with about ten minutes of hands-on time. There is nothing to install and nothing to configure.
  • [claimed-docs] https://docs.lovable.dev/introduction/create-an-account.mdAnyone with an email address can sign up for free... Lovable automatically creates your first personal workspace on the free plan
  • [claimed-docs] https://docs.lovable.dev/introduction/lovable-for-enterprise.mdcentralized identity, granular access controls, workspace-wide security oversight, scheduled Deep scans, audit logs, regional code hosting

Openness = 16.8 ÷ 80 × 100 = 21.0

Built-in AI46.7/100×0.15 of the PA blend

Inside-out: how agentic the product itself is for its users — built-in assistants, autonomous features.

Get AI-generated insights and suggestions from my data inside the productweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [claimed-docs] https://docs.lovable.dev/features/database.mdFor direct database access, use the SQL editor at Cloud tab → SQL editor
  • [claimed-docs] https://docs.lovable.dev/features/database.mdFor direct database access, use the SQL editor at **Cloud tab → SQL editor**
  • [claimed-docs] https://docs.lovable.dev/features/ai.mdLovable's built-in AI connector handles that setup for you, so you can add AI features to your app by describing what you want to build.
  • [claimed-docs] https://docs.lovable.dev/features/database.mdDescribe the data your app needs in chat, and Lovable creates the tables and schema for you.

Set up automations that run autonomously in the backgroundweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [claimed-docs] https://docs.lovable.dev/features/agent-mode.mdBuild mode (previously Agent mode) is Lovable's autonomous execution mode, designed to implement changes directly in your project. When you give Lovable a task, it takes ownership of execution end to end.
  • [claimed-docs] https://docs.lovable.dev/features/agent-mode.mdBuild mode (previously Agent mode) is Lovable’s autonomous execution mode, designed to implement changes directly in your project. When you give Lovable a task, it takes ownership of execution end to end.
  • [claimed-docs] https://docs.lovable.dev/features/agent-mode.mdLovable working on a request doesn't block you. Send a follow-up, a correction, or a new idea at any time to steer the work
  • [claimed-docs] https://docs.lovable.dev/introduction/lovable-for-enterprise.mdcentralized identity, granular access controls, workspace-wide security oversight, scheduled Deep scans, audit logs, regional code hosting

Delegate tasks to a built-in AI assistant inside the productweight 3

3 (weight) × 8 (quality) × 1.0 (full) = 24.0 of 30 max

  • [claimed-docs] https://docs.lovable.dev/features/agent-mode.mdBuild mode (previously Agent mode) is Lovable's autonomous execution mode, designed to implement changes directly in your project. When you give Lovable a task, it takes ownership of execution end to end.
  • [claimed-docs] https://docs.lovable.dev/features/agent-mode.mdBuild mode (previously Agent mode) is Lovable's autonomous execution mode, designed to implement changes directly in your project.
  • [claimed-docs] https://docs.lovable.dev/features/agent-mode.mdBuild mode (previously Agent mode) is Lovable’s autonomous execution mode, designed to implement changes directly in your project. When you give Lovable a task, it takes ownership of execution end to end.
  • [claimed-docs] https://docs.lovable.dev/features/agent-mode.mdLovable working on a request doesn't block you. Send a follow-up, a correction, or a new idea at any time to steer the work
  • [claimed-docs] https://docs.lovable.dev/features/agent-mode.mdLovable applies changes directly to your project when using Build mode. All modifications are visible through file diffs and summaries.
  • [claimed-docs] https://docs.lovable.dev/features/projects/editor.mdyou describe what you want in the chat panel on the left, and you watch your app take shape in the preview on the right
  • [claimed-docs] https://docs.lovable.dev/features/projects/chat.mdyou can also ask Lovable to run project actions from chat, for example publish my app, deploy this project, ship it, or find me a domain for my bakery
  • [claimed-docs] https://docs.lovable.dev/features/publish.mdAsk Lovable to publish, deploy, ship, or go live, and it handles the deploy for you while respecting all publish-related workspace settings and permissions.
  • [community] https://news.ycombinator.com/item?id=44377495"I'm using Lovable heavily for PM prototyping and it's great. I think, if anything, current subscription may be too cheap!"
  • [community] https://news.ycombinator.com/item?id=44377495Startup CTO uses Lovable heavily for internal dashboards/CRUD tools; saved the equivalent of two full-time developers, but generated code is only okay, lacks sane defaults, abuses the 'any' type.

Operate the product with natural-language commandsweight 2

2 (weight) × 9 (quality) × 1.0 (full) = 18.0 of 20 max

  • [claimed-docs] https://docs.lovable.devYou describe what you want to build, and Lovable generates a working application that includes frontend, backend, database, authentication, and integrations, all backed by editable code.
  • [claimed-docs] https://docs.lovable.dev/features/agent-mode.mdBuild mode (previously Agent mode) is Lovable's autonomous execution mode, designed to implement changes directly in your project. When you give Lovable a task, it takes ownership of execution end to end.
  • [claimed-docs] https://docs.lovable.dev/features/agent-mode.mdBuild mode (previously Agent mode) is Lovable’s autonomous execution mode, designed to implement changes directly in your project. When you give Lovable a task, it takes ownership of execution end to end.
  • [claimed-docs] https://docs.lovable.dev/features/database.mdDescribe the data your app needs in chat, and Lovable creates the tables and schema for you.
  • [claimed-docs] https://docs.lovable.dev/features/projects/editor.mdyou describe what you want in the chat panel on the left, and you watch your app take shape in the preview on the right
  • [claimed-docs] https://docs.lovable.dev/features/projects/chat.mdyou can also ask Lovable to run project actions from chat, for example publish my app, deploy this project, ship it, or find me a domain for my bakery
  • [claimed-docs] https://docs.lovable.dev/features/publish.mdAsk Lovable to publish, deploy, ship, or go live, and it handles the deploy for you while respecting all publish-related workspace settings and permissions.
  • [community] https://news.ycombinator.com/item?id=44377495"I'm using Lovable heavily for PM prototyping and it's great. I think, if anything, current subscription may be too cheap!"
  • [community] https://news.ycombinator.com/item?id=44377495Startup CTO uses Lovable heavily for internal dashboards/CRUD tools; saved the equivalent of two full-time developers, but generated code is only okay, lacks sane defaults, abuses the 'any' type.

Built-in AI = 42.0 ÷ 90 × 100 = 46.7

Automation6.0/100×0.15 of the PA blend

Depth of automation primitives — rules, scheduling, bulk operations, webhooks.

Perform bulk operations across many items at onceweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Define rules that trigger actions automatically on eventsweight 3

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Schedule recurring jobs or workflowsweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Version, review, and roll back my automationsweight 1

1 (weight) × 5 (quality) × 0.6 (partial) = 3.0 of 10 max

  • [claimed-docs] https://docs.lovable.dev/integrations/github.mdyou can export and sync your project to GitHub: back up your code, review changes in pull requests, work locally in your IDE, test features on branches, and deploy outside Lovable
  • [claimed-docs] https://docs.lovable.dev/integrations/github.mdback up your code, review changes in pull requests, work locally in your IDE, test features on branches, and deploy outside Lovable
  • [claimed-docs] https://docs.lovable.dev/integrations/git-sync-overview.mdGit sync connects a Lovable project to a repository you own on GitHub or GitLab, and keeps the two in sync automatically
  • [claimed-docs] https://docs.lovable.dev/tips-tricks/lovable-telegram-bot.mdCheck edit history and review what changed... Query your project database with read-only queries
  • [claimed-docs] https://docs.lovable.dev/integrations/git-sync-overview.mdWork locally in your IDE. Clone the repository, edit and commit locally, and push. Your changes sync back into Lovable.

Automation = 3.0 ÷ 50 × 100 = 6.0