The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
Agentic AI Workflow for Real Estate Lead Enrichment (USA)
I built a production-grade, engineering-first workflow that turns minimal “clues” (company name, property address, or Tax ID) into a structured owner/contact dossier.
Stack: self-hosted n8n, OpenAI (GPT-5), Airtable (UI + database), Google Search, RealTrack (closed system)
Input → Output: 1–3 clues in → a complete enriched profile in ~60–120 seconds (with citations/links to sources) ready for sales outreach and due diligence.
The Problem (How the team worked before)
The client’s manual process looked like “crossfire research”:
- Find a company name + street / Tax ID
- Open multiple platforms/tabs
- Cross-check signals, collect evidence
- Compile a dossier in spreadsheets/CRM
This was slow (20–45 minutes per request), error-prone, and hard to scale.
I delivered an end-to-end agentic workflow that automates the same multi-platform research the team did manually — but faster and with consistent formatting.
1. ~90% reduction in pre-call research time per lead
2. ~60–120 seconds per lookup vs 20–45 minutes manually
3. ~$0.02 per enrichment request (token cost; excluding optional external services)
4. Self-hosted n8n: dramatically lower operational costs vs cloud pricing at scale
Amazing job Oleh!
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
I'll be honest — my last three posts flopped.
Took me a minute to see why. I'd been writing hot takes when I should've been writing what actually helps.
Here's a small automation I shipped last week that none of my "big" posts will beat for value:
A client kept losing meeting notes. Calls in Google Meet, transcripts in their inbox, action items nowhere. Standard SMB chaos.
The fix:
Google Meet transcript → n8n webhook → GPT extracts action items + owner → posts to their Slack channel + appends to a Notion database.
Now every meeting ends with a clean action list, automatically assigned. They stopped using the word "follow-up" in calls.
Not glamorous. Not contrarian. Just useful.
What's the smallest automation that made the biggest difference in YOUR work? Drop it below — I'm collecting ideas for clients. 👇
#n8n #Automation #Productivity
A Telegram bot built as a parallel layer to a productivity system, designed to intercept moments of negative impulse and convert them into structured reflection conversations.
How it works:
Every user message triggers an AI intervention conversation grounded in the user's Chief Definite AIM, recent insights, current goal pacing, and reflection history
Voice messages auto-transcribed via OpenAI Whisper, treated as text turns in the conversation
/done command ends the session, prompts trigger word + outcome (avoided / indulged / unclear), persists everything to SQLite for downstream daily summary integration
/restart wipes session state for fresh context
System prompt is brother-tone, AIM-grounded, 80–200 words per response, deliberately not therapy-speak
Runs in the same Node process as a separate productivity bot — two bots, two tokens, one codebase.
Tech: Node.js, Telegram Bot API, Claude API, OpenAI Whisper, SQLite.
The idea of intercepting negative impulse moments in real time is genuinely clever. most productivity tools wait for you to come to them — this flips it. voice transcription via Whisper is a smart touch too, removes friction completely. how's the response latency holding up in practice?
Designed, built and deployed a Prospect Finder tool.
AI-Powered Lead Intelligence & Outreach Platform.
Built a fully custom, AI-powered prospecting and outreach platform from the ground up to power an entire sales operation solo, without an engineering team.
The platform functions as a complete sales intelligence command center, pulling prospect data across multiple sources simultaneously; Google Maps, LinkedIn, business websites, Yelp, Facebook, license databases, and directories and scoring each lead with a proprietary AI Fit Score to prioritize outreach by conversion likelihood.
From there, the system manages the full 8-touch outreach campaign lifecycle per prospect, tracking each contact’s position across the sequence in real time. When prospects reply, the platform surfaces AI-generated response suggestions tailored to the conversation context, allowing instant, intelligent follow-up with a single “Approve & Send.”
What I built:
[] Search Command Center with multi-source data scraping (Google Maps, LinkedIn, Yelp, Facebook, Licenses, Directories)
[] AI Fit Scoring engine that ranks prospects by conversion likelihood
[] 8-touch campaign status tracker per contact
[] AI-suggested reply system with Ignore / Edit / Approve & Send workflow
[] Lead management dashboard with overview, replies, leads, campaigns, network, and archives modules
[] Export functionality for pipeline data
Platform tools of dev: Agentic AI development workflows, Claude API, n8n automation, no-code platforms.
End product output: A single operator running a sales intelligence and outreach system that would typically require a dedicated SDR team and a $30k+/year software stack. Built and deployed solo in weeks.
Trending
Claude
Claude has entered the design space. How are you using Claude Design?
Contra University
Learn from expert creatives how to earn more using next-gen AI tools.
creativeaiflow
Creative AI workflows are evolving. What tools do you use, and what are their strengths and weaknesses?
portfolioreview
The best portfolios tell a story, not just show a grid. Share yours for feedback.
freelancerlife
Freelancer life is wins, pivots, and everything in between. What’s yours right now?