The situation
An end-to-end pipeline that scrapes ad data, removes duplicates, enriches companies from the open web, scores them with GPT, and verifies matches against UK Companies House, before a sales rep ever sees the row.
All case studies
Automation
AI Lead Generation & Qualification
Meta Ads Library scrape → dedupe → Serper enrichment → GPT scoring → Companies House verify.
n8nApifyOpenAI / GPTSerperCompanies House API
The problem
Raw scraped leads were noisy: duplicates, wrong countries, and companies that were not worth a call. Reps wasted time qualifying by hand.
What we built
A form-triggered n8n pipeline: Apify Meta Ads scrape, CRM/exclusion dedupe, country normalize, Serper + GPT enrichment and scoring, Companies House match, and idempotent status tracking for safe re-runs.
What the system does
- Automated Meta Ads Library scraping via Apify
- Smart deduplication against CRM and exclusion lists
- AI enrichment and scoring (Serper + GPT)
- Official Companies House verification
- Status tracking so re-runs never double-process a lead
How it’s wired
The production n8n workflow , triggers, retries, and write-backs , not a slide-deck diagram.
Similar systems
All case studiesRelaydeskProduct / Internal Build
Relaydesk: WhatsApp Automation SaaS
Multi-tenant messaging architecture with queues, webhooks, and campaigns.
Next.jsTypeScriptTailwind
Read case study CITA MonitorWorking Software
CITA Monitor: Appointment Availability & Auto-Booking
Working software that watches ICP+ slots and alerts over Telegram.
PythonFastAPISQLite
Read case study AI Voice ReceptionistProduct / Concept
AI Voice Receptionist
Phone conversations that collect structured data and write back to a CRM.
VapiTwilioDeepgram
Read case study