Lighthouse
Lighthouse is an AI-powered deal qualification engine for Vercel enterprise sales.
Core trick
Streams a six-stage URL analysis over SSE, combining detected tech stack and Core Web Vitals into a Gemini-scored deal brief.
Description
Lighthouse is an AI-powered deal qualification engine for Vercel enterprise sales. Paste any website URL and in under 60 seconds it returns a complete sales package: tech stack detection, Core Web Vitals audit, deal score (0-100), migration strategy, architecture diagrams, PoC proposal, and audience-targeted talking points. Built with Next.js 15, Gemini 2.5 Pro, and Cortex graph memory, every analysis is persisted so the system learns migration patterns across prospects.
README excerpt
# Lighthouse > AI-powered deal qualification and value engineering agent for Vercel enterprise sales. [](https://github.com/michaeldarlington/lighthouse/actions/workflows/ci.yml) [](#testing) [](#testing) --- ## What It Does Enter a URL. In roughly 60 seconds, Lighthouse runs a full pre-sales engineering workflow and delivers an enterprise-ready prospect briefing. The pipeline executes six stages via a real-time SSE stream: | Stage | What Happens | |-------|-------------| | **1. Fetch** | Retrieves the page, captures response headers, and extracts raw HTML for analysis. | | **2. Tech Stack Detection** | Identifies the full composable architecture -- framework, hosting, CDN, CMS, commerce, search, auth, payments, monitoring, analytics, third-party scripts, and rendering strategy. Runs in parallel with performance. | | **3. Performance Measurement** | Queries PageSpeed Insights and Chrome UX Report for lab and real-user metrics (LCP, TTFB, CLS, FID, INP). Runs in parallel with tech stack. | | **4. Prospect Qualification** | Scores the deal 0--100, classifies traffic tier, assesses Vercel fit, and scrapes the careers page for migration signals (frontend hiring, headless mentions, replatform activity). | | **5. Value Engineering** | Models revenue imp