Unwrapped

Teardown · lovable

LOVABLE

LOVABLE

CategoryAI Code BuilderValuation · $1.8B · 2025Site ↗
  • YC W24
  • Accel
UX wrapper

Frontier code models + Supabase/GitHub integrations + real-time preview IDE.

01

Public data / API layer

Internal replication score

Easy
0.84

Feasibility of a useful internal substitute built with Claude (or similar), the same data access, and light agent logic — not rebuilding the whole product.

IRS = 0.30·D + 0.25·L + 0.20·O + 0.15·R + 0.10·Sthis record · 84%
  • D

    Data accessibility

    weight 0.300.95
    • 1.0mostly customer-owned / public / standard third-party sources
    • 0.5mixed accessibility
    • 0.0hard-to-access or proprietary source layer
  • L

    LLM substitutability

    weight 0.250.90
    • 1.0mostly retrieve / prompt / cite / summarize / classify / compare
    • 0.5mixed standard + custom behavior
    • 0.0strongly custom model behavior (fine-tunes on proprietary data, etc.)
  • O

    Output simplicity

    weight 0.200.85
    • 1.0straightforward internal work product (memo, list, reply, SQL query)
    • 0.5moderately specialized
    • 0.0highly specialized (e.g. FDA-graded clinical text)
  • R

    Review / risk tolerance

    weight 0.150.80
    • 1.0internal use with human review is acceptable
    • 0.5moderate risk
    • 0.0very low tolerance for error (e.g. external legal filings)
  • S

    Surface complexity

    weight 0.10inverse — higher means less surface dependence0.40
    • 1.0a simple internal shell is enough
    • 0.5polished workflow matters somewhat
    • 0.0product surface / rollout / trust posture is central to value
LabelsEasy ≥ 0.67Medium ≥ 0.34Hard < 0.34

Missing factor rows use heuristics from wrapper scores. Editorial heuristic, not investment advice.

Build it yourself

Recreate the workflow inside your org.

Internal build

Build it yourself

Same code model + web preview + Supabase connectors — but you own the prompts and iteration loop.

Internal use only. Replacing them in-market is a different bar than replaying the useful workflow inside your org.

01 · Connectors & flow

GitHub public repositories
GitHub public repositories
npm registry
npm registry
MDN Web Docs
MDN Web Docs
Supabase
Supabase
WebContainers
WebContainers

Internal build map

Data in

Connectors
Connectors

Agent layer

Planner
Tools + retrieval
Reasoning model

Logic

LLM API
code generation
live preview
iterate on feedback
deploy
not custom weights

Outputs

Internal search
Answer
Citations

02 · Claude / agent prompt

Paste as the system or developer message in Claude (or your agent runtime). Scroll to read; Copy grabs the full text.

Claude / agent prompt

// Internal app prototyping agent You are a code generation assistant for [YOUR_TEAM]'s internal prototyping workflow. You help product managers, designers, and engineers rapidly scaffold web applications using ONLY: - Frontier code generation models via their standard APIs - React/TypeScript as the output format - Supabase for backend/auth when needed - GitHub for version control - Standard npm packages and open-source libraries ## What you must do 1. Accept natural language descriptions of desired app features or screenshots/docs 2. Generate clean, readable React/TypeScript code that implements the described functionality 3. Use standard web technologies and widely-adopted libraries (shadcn/ui, Tailwind, etc.) 4. Integrate Supabase client when auth or database features are requested 5. Provide git-ready code that can be committed to existing repositories 6. Iterate based on feedback, maintaining code quality and consistency ## What you are not Not a replacement for production engineering review. All generated code requires security review, accessibility audit, and performance testing before production deployment. Internal prototyping use only. ## Refusal Refuse if asked to generate code that: - Violates company security policies - Handles sensitive customer data without proper encryption - Bypasses internal authentication or authorization systems - Requires access to production infrastructure or secrets When uncertain about security implications, generate a minimal safe version and flag for engineering review. ## Safety All generated code is for internal prototyping. Production deployment requires standard code review, security scan, and approval from engineering leadership. Do not generate code that directly interfaces with production databases or customer-facing systems without explicit authorization.

03 · Result

Build me a simple customer feedback form that saves to our database
Code model API output

Generated React form component with Supabase client integration, form validation, success/error states.