lovable.dev — AI Readiness Score: 60/100

doclight — ai Readiness Report

lovable.dev

Pages analyzed (12)

llms.txt included https://lovable.dev/llms.txt 200
llms-full.txt https://lovable.dev/llms-full.txt 404
llms.txt included https://docs.lovable.dev/llms.txt 200
llms-full.txt included https://docs.lovable.dev/llms-full.txt 200
marketing included https://lovable.dev/ 200
pricing included https://lovable.dev/pricing 200
docs included https://docs.lovable.dev/integrations/introduction 200
other https://lovable.dev/guides 200
docs included https://docs.lovable.dev/integrations/mcp-servers 200
docs included https://docs.lovable.dev/integrations/ai 200
marketing https://rules.lovable.dev/ 200
marketing https://status.lovable.dev/ 200

llms.txt found

AI READINESS SCORE

Lovable is an AI-powered platform for building full-stack web and mobile apps, websites, and internal tools from natural-language prompts. Users describe what they want and Lovable generates the code, with a built-in backend (Lovable Cloud), built-in AI features, and a broad library of integrations including app connectors (Stripe, Shopify, Supabase, etc.) and chat connectors via MCP servers (Notion, Linear, Atlassian). It targets individuals, fast-moving teams, and enterprises, offering hosting, custom domains, collaboration, and governance features.

Dimension Breakdown

Discoverability

Clear product naming, marketing site, two llms.txt files, and an llms-full.txt make the product highly discoverable and categorizable by AI agents.

Comprehension

The product's purpose, use cases, integrations, and plan distinctions are explained clearly across docs and marketing pages.

Setup clarity

Setup is described conceptually for a human using the UI (menus, command palette), but there is no programmatic/API onboarding path for an autonomous agent.

Documentation

Extensive human-oriented docs with llms.txt and llms-full.txt indexes, though much is UI-driven rather than agent-actionable.

Pricing clarity

Pricing tiers, credit allotments, and feature differences are listed clearly, though credit-to-usage conversion details remain vague.

Integration examples

Many integrations and MCP support are described, but no concrete code samples, API endpoints, or OpenAPI spec are provided for programmatic use.

Agent Journey

✓

Discover

✓

Understand

Setup

Setup is described only as UI workflows with no programmatic account creation, authentication, or API key flow documented for an agent.

Use

Without an API, OpenAPI spec, or code examples, an autonomous agent cannot programmatically build or operate apps beyond MCP-style context provision.

Confusion Points

high No public REST/API or OpenAPI spec is exposed; the platform is operated through natural-language prompts in a UI All docs/integration pages
med The 'credit' concept is referenced for billing and usage but never quantitatively defined (what one credit buys) pricing page
med LOVABLE_API_KEY managed secret is mentioned but no usage instructions, scopes, or examples are given integrations/introduction
med Setup steps reference UI paths (Connectors → App connectors → Lovable AI) that an agent cannot navigate programmatically integrations/ai

Missing Information

Is there a public API or SDK an agent can call to create or manage Lovable projects programmatically?
How is the LOVABLE_API_KEY obtained and used, and what endpoints does it authenticate?
What exactly does one credit equate to in terms of usage or model calls?
Are there code examples or request/response schemas for app connectors and the built-in AI connector?
What models are supported for built-in AI and what are their per-model costs and rate limits (page was truncated)?
How can an agent authenticate and sign up without manual UI interaction?

Improvements

Publish an OpenAPI/Swagger spec and a developer API reference so agents can programmatically create and manage projects.
Add concrete code examples (curl, JS, Python) for using app connectors, the built-in AI connector, and LOVABLE_API_KEY.
Define the credit unit quantitatively and map credits to specific actions/model usage on the pricing page.
Document a programmatic onboarding/authentication flow including API key generation and scopes.
Provide machine-readable model lists with pricing and rate limits for the built-in AI features.
Include a dedicated 'for AI agents' integration guide describing the supported MCP interface and capabilities in structured form.