A B2B sales team was spending most of their time on manual prospecting: searching LinkedIn for leads, qualifying them one by one, and writing personalized outreach messages. The process was slow, inconsistent, and couldn't scale.
The Solution
I built an AI-powered prospecting system that automates lead discovery, qualification, and personalized outreach at scale.
How it works:
The system searches LinkedIn and other sources based on ideal customer profile criteria
Discovered leads are automatically enriched with company data, role info, and activity signals
Claude API scores and qualifies each lead based on fit criteria
Personalized outreach messages are generated for each qualified lead, referencing specific details from their profile
Qualified leads and draft messages are queued in Supabase for sales team review and approval
Key features:
Automated lead discovery from LinkedIn and web sources
AI-powered lead scoring and qualification via Claude API
Hyper-personalized outreach message generation
Lead pipeline dashboard with filtering and prioritization
Campaign tracking with response rate analytics
Human-in-the-loop approval before any message is sent
Tech Stack
AI: Claude API
Backend: Python
Database: Supabase
Integrations: LinkedIn
Results
Lead discovery volume increased 10x with same team size
Outreach personalization improved response rates from 3% to 14%
Sales team spends 80% less time on manual prospecting
Pipeline value increased 3x within the first 2 months