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
Week 1 of selling a $300 automation with no client work to show. The honest numbers
About 60 personalized emails to small US web and marketing agencies. 10 LinkedIn connection requests. 3 marketplace listings live: Fiverr, Upwork and Contra. Real replies so far: 0 (two out-of-office auto-replies).
What I learned: a designed HTML email landed in Gmail's Promotions tab in my own test while plain text landed in Primary, so I'm testing both. And every opener needs one true detail from the agency's own site. It is slow, but it is the only part that doesn't read like a template.
What we sell: when a website inquiry comes in, it lands in a Google Sheet, the owner gets an alert, and the customer gets an instant reply. Built in n8n, white-label for agencies, $300 flat, 4 working days. The first 3 launch partners pay only after it is live and tested.
Working demo: https://www.oqviangroup.com/offer
Honest numbers are useful, thanks for sharing. Two things that usually move week two: send to a smaller list where you can name a specific reason per company (a tool they run, a hiring post, a broken form), and keep it plain text with one question. For finding companies by the...
Honest numbers are useful. One thing that moved my reply rate: only email agencies whose site shows the stack your automation plugs into. If it is HubSpot only, filter for HubSpot first. I wrote down how I build those lists: https://stackshortlist.dev
Thanks, both points are useful. For week 2 I'm cutting the list down and giving each agency one specific reason from its own site. I'll share what changes in the next update.
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
Challenges
View all
Related posts
🚀Starting fresh?
How about 5 hours free for a verified client → then paid projects.
Would you take that deal to land your first client?
Vote below 👇 and comment your skill if you're in
2 voted
50%
2 voted
50%
4 votes
Closed
Time is the most valuable thing you can get you can't buy it👍
🟢 I built an AI agent that reads invoices so humans don't have to. Manual invoice entry is slow, boring, and full of typos. So I automated it end to end in n8n.⚫
Here's how it works:
🟢 Invoice comes in: A webhook receives the PDF through a POST request
⚫ Text extraction: The file is parsed and the text pulled out
🟢 Safety check: If the file is invalid, the system responds with an error right away
⚫ Smart chunking: Large invoices are split into smaller pieces so nothing gets cut off or lost
🟢 AI extraction: A loop sends each chunk to an Information Extractor powered by Anthropics Claude, which pulls out the fields the client needs (vendor, invoice number, dates, line items, totals)
⚫ Merge and validate: The results are combined into one record and checked before they are sent
🟢 Clean JSON response: The structured data goes straight back through the webhook The hardest part was'nt the AI. It was making it production-ready. 💡
Long, multi-page invoices break most simple AI workflows because they exceed the models limits. Chunking, looping, merging, and validating are what let this handle large invoices reliably. Where this fits in the real world:
⚫ Accounting and finance teams processing hundreds of vendor invoices
🟢 Businesses syncing invoice data into ERPs or spreadsheets
⚫ Freelancers and agencies automating their billing workflows What used to take minutes per invoice now takes seconds, with no copy-pasting. ⚡ I'm currently going deeper into n8n and AI automation.
If you are looking to automate document processing or any repetitive workflow, lets connect! 🤝
#n8n #Automation #AIAutomation #InvoiceProcessing #WorkflowAutomation #Claude #FullStackDeveloper #NoCode
🚀 Just Built a Sales & Marketing AI System — 3 Agents in 1!
I noticed something while working with B2B sales teams:
❌ Leads come in, but follow-ups get delayed
❌ Marketing team spends hours creating content
❌ Sales team wastes 15+ hours/week on manual tasks
❌ Hot leads go cold because no one follows up fast enough
I built a Sales & Marketing AI System that solves all of this:
🤖 AGENT 1: Lead Qualification
✅ Scores leads as HOT/WARM/COLD automatically
✅ Logs everything to Google Sheets/CRM
📧 AGENT 2: Multi-Channel Follow-Up
✅ Email sequences (Day 0, 2, 5, 7)
✅ WhatsApp + LinkedIn outreach
✅ Reply detection
📝 AGENT 3: Marketing Content
✅ Social media posts generate kare
✅ Email campaigns banae
✅ Content calendar maintain kare
Built with: n8n + OpenAI + Google Sheets + Gmail + Telegram
Result: 60% higher conversion, 15+ hours/week saved per rep.
Want this for your business? DM me 📩
#AIAutomation #SalesAutomation #MarketingAutomation #n8n #B2BSales
