Production lead-generation platform for a B2B sales team: Claude-powered prospect search, research briefs and outreach drafts, automated lead ingestion and scoring, and AI voice agents on live phone calls.
The client's sales team needed a single system to find, research and contact prospects. Lead data was scattered across public sources, prospect research and outreach writing were manual, and approvals, notifications and lead routing between team members were not automated.
Built the platform end to end (React, TypeScript, Supabase/PostgreSQL), working directly with the client to gather change requests and ship updates. - LLM features (Anthropic Claude API): natural-language prospect search, AI-generated research briefs and AI-drafted outreach messages. - Data pipelines: scheduled scrapers and HTML/PDF parsing of public sources on GitHub Actions cron, with deduplication and entity resolution, feeding a configurable lead-scoring engine. - Voice AI: built and deployed AI voice agents that handle live phone calls using Deepgram, Voiceflow and Retell. - Automation: approvals, notifications and lead routing with n8n and Zapier. - Security: Row-Level Security, role-based access control, JWT-verified endpoints and restricted CORS.
In production and used daily by the client's sales team. Prospect search, research briefs and first-draft outreach are now generated by AI instead of written by hand; lead data from public sources is ingested, deduplicated and scored automatically on a schedule; AI voice agents handle live phone calls; and approvals, notifications and lead routing run automatically.
In daily production use by the client's sales team. Manual prospect research and outreach drafting replaced by AI-generated research briefs and drafts; lead ingestion, deduplication and scoring from public sources fully automated on a schedule; live phone calls handled by AI voice agents; approvals, notifications and lead routing automated end to end.