RoofEra
AI-powered sales and engagement platform I built for roofing companies. Acts as a virtual inside sales representative — answering calls, texting leads, following up, and booking inspections automatically.
roofera.aiTech Stack
Highlights
- Built the entire platform from scratch — database architecture, API layer, frontend, AI agents, and billing
- Developed AI agents using Vercel AI SDK with models from OpenAI and Anthropic (Claude)
- Built MCP servers and custom tools that give AI agents the ability to run complex operations
- Implemented RAG with text embeddings and similarity searches against a vector database for accurate, context-aware responses
- Used Langfuse for LLM observability — tracing and analyzing all AI agent conversations to monitor performance and debug issues
AI Agent Capabilities
Inbound Call Handling
AI voice assistant that answers incoming calls 24/7, handles common questions, collects lead details, and books inspections
Speed-to-Lead Texting
Instantly texts new leads from Facebook ads, Google ads, website forms, and other sources
Missed Call Text-Back
Automatically texts callers whose calls were missed to re-engage and book appointments
Automated Inspection Booking
Schedules confirmed appointments directly onto connected calendars with real-time availability
Lead Qualification
Collects structured data (project type, address, urgency, insurance status, photos, timeline) to deliver qualified appointments
Quote Follow-Up
Manages SMS follow-ups after quotes are delivered, handles objections, and prompts next steps
Review & Referral Requests
Texts customers post-job to request reviews and referrals, generating additional inbound opportunities