Skip to content

About

LeadGen.ai

Resources

Stars

2 stars

Watchers

1 watching

Forks

Latest commit

 

History

52 Commits

Folders and files

Repository files navigation

AI-Powered Lead Generation & Decision Platform

Smart Client Evaluation with Collaborative AI Analysis using IBM Granite Models

image


Overview

Our platform revolutionizes B2B lead generation by combining machine learning predictions with AI-driven debate to optimize client selection. The system analyzes historical data to identify promising clients, conducts targeted research, and employs competitive AI agents to simulate strategic discussions before finalizing engagement decisions.


Key Features

1. Smart Client Prediction Engine

  • Analyzes historical sales/CRM data using ML models
  • Classifies clients as "high-potential" or "high-risk"
  • Filters out unproductive leads before further analysis

2. Automated Client Intelligence

  • Integrated web scraper gathers real-time company data
  • Contextualizes information based on your business specialty
  • Supports custom company inputs (e.g., "Boeing" for AI consulting analysis)

3. Competitive AI Debate System

  • Two specialized agents argue For and Against engagement
  • Agents reference scraped data and financial/strategic factors
  • Dynamic discussion format surfaces risks and opportunities

4. Judge Agent Decision Module

  • Final verdict with nuanced outcomes:
    • Approve
    • Reject
    • Proceed with Caution (conditional approval)
  • Provides clear rationale for human review

Workflow Process

diagram-export-27-02-2025-21_15_34

  1. User Input

    • Enter target company name (e.g., "Boeing")
    • Specify your company's specialization (e.g., "AI Consulting")
  2. Data Processing

    • ML model evaluates client potential from historical data
    • Web scraper collects fresh company intelligence
  3. AI Analysis Phase

    • Competitive agents debate client suitability
    • Arguments focus on strategic alignment and risk factors
  4. Final Decision

    • Judge agent delivers verdict with supporting rationale
    • Exportable summary for team review
  5. Next Steps

    • Approved leads: Initiate outreach campaigns
    • Conditional approvals: Trigger follow-up investigations

Technical Architecture

Frontend: Next.js (Vercel-hosted) interactive dashboard
Backend: FastAPI handling ML predictions and debate logic
AI Core:

  • Custom fine-tuned LLMs for agent discussions
  • Hybrid scraping system (public data + licensed sources)
  • Modular decision engine supporting multiple outcome types

Key Benefits

✅ Risk Reduction: Dual-layer filtering (ML + AI debate) minimizes bad investments
✅ Strategic Insights: Agent discussions reveal non-obvious pros/cons
✅ Time Efficiency: Automates research & initial evaluation phases
✅ Adaptable: Handles diverse industries and company sizes


Live Demo

See the system in action:

FullDemo-LeadsGen-AI-IBM-Granite.-.Made.with.Clipchamp.mp4

PS: I have shutdown the Ibm models deployment for resources consumption reasons.

About

LeadGen.ai

Resources

Stars

2 stars

Watchers

1 watching

Forks

Releases

Packages

Used by

Contributors

Languages