[b.] creative | Auction Intel Lead Generation Platform

Auction Intel — Project Portfolio Summary

Auction Intel (auctionintel.app) — An AI-powered lead intelligence platform that discovers nonprofit auction events and delivers verified, sales-ready leads to event-services vendors.

The Problem It Solves

Companies that provide services to nonprofit auction events (auctioneers, event planners, catering, A/V rental) have no reliable way to find upcoming events before their competitors. Manually searching thousands of nonprofit websites is impossibly time-consuming. Auction Intel automates this: upload a list of nonprofit domains, and the platform uses AI web research to discover which organizations are planning auction events, extract event details, find decision-maker contacts, verify email deliverability, and deliver structured billable leads — all in real time.

Platform Overview

LayerTechnology
BackendPython 3 / Flask (~6,800 lines in app.py alone)
AI EngineClaude Haiku 4.5 with web search via Poe Bot API
DatabasePostgreSQL on Railway (14 tables)
PaymentsStripe (Payment Intents, webhook-driven wallet)
EmailResend API (20 HTML templates)
Email VerificationEmailable API (real-time deliverability scoring)
IRS DataPostgreSQL table of IRS 990 nonprofit filings
Real-Time StreamingServer-Sent Events with reconnect+ polling fallback
DeploymentRailway (auto-deploy on push to main)
FrontendServer-rendered HTML, Tailwind CSS, vanilla JS
API ClientStandalone Python CLI for headless batch operation

Technical Architecture

System ComponentImplementation Details
LLM Service LayerWraps an LLM with web search into a metered SaaS with per-result billing, tiered pricing, and real-time wallet deductions.
Real-Time Event StreamingSSE with numbered event replay, heartbeat keepalives, 20-attempt reconnect, automatic polling fallback, and per-domain checkpointing.
Semantic Cache LayerTTL varies by result type: found events expire after the event date, not-found in 30 days, errors in 7 days, uncertain in 1 hour.
Multi-Stage LLM ParsingFour extraction strategies in sequence plus data-driven status override that trusts extracted fields over model self-classification.
End-to-End Data PipelineIRS data (prospect discovery) → AI web research (event verification) → email validation (lead quality) → Stripe (monetization) → 20-email lifecycle (retention) — all in a single Flask app with zero external job queues.

Platform Scale

SystemMetric
Lines of Python~9,500 across 5 core files
PostgreSQL tables14
Flask routes50+
Email templates20
CSV output columns18 per lead
IRS filter fields30+
Max nonprofits per job5,000
Max IRS results per query10,000

Video Tour