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
Working in a construction company I saw accountants doing data entry by looking at pdfs of bills coming from sites and manually typing data in Tally I realized we can automate this process so I built n8n workflow which converts PDFs coming through emails into google sheet also saving the pdf attachments in drive folder.
Read more about it on my medium blog https://jyoti03.medium.com/construction-finance-has-a-visibility-problem-i-fixed-it-with-an-ai-pipeline-289761bbda5a
jyoti03.medium.com
Construction Finance Has a Visibility Problem — I Fixed It With an AI Pipeline
When I joined our construction company, I expected chaos.
@jyoti vyas Routing emailed bill PDFs into Google Sheets while archiving attachments in Drive should cut a lot of duplicate entry. How do you handle low-confidence fields before they reach Tally?
I handle it with a validation layer between extraction and accounting.
In my n8n invoice workflow, I deliberately don't treat the AI's output as truth. I validate the extracted fields against business rules and cross-check related values before allowing the record to move...
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
Trending
retrofuturism
Share your favorite designs from the past exploring the distant future. Or your own take on the aesthetic 🚀
halftone
Dots. Texture. Grain. Let's see your designs using the halftone technique.
Midjourney
Creatives are showing off what they're making with Midjourney.
colorgrade
Video editors sound off: How do you enhance the mood of your video in color grading?
Related posts
⚡ Automation Isn't the Hard Part. Knowing What to Automate Is.
Everyone talks about AI, n8n, Make, Zapier, and no-code automation. But there's a step people often skip:
What should actually be automated?
Not every manual task needs automation.
Sometimes the workflow is already too complicated.
Sometimes the process changes every week.
Sometimes automating a bad process just makes the bad process faster. 😅
Before building an automation, I like to ask
→ 📈 Does it happen often enough to matter?
→ ⏱️ Is it wasting meaningful time?
→ ⚠️ Does manual work create mistakes?
→ 🚀 Will automation actually improve the workflow?
Only after understanding the workflow should you choose the right solution — whether that's automation, AI, or simply a smarter process.
Don't automate everything.
Automate what shouldn't require a human.
What's one process in your work that you think is ready for automation? 👇
#DigitalTransformation #FutureOfWork #Startups #Entrepreneurship #BusinessGrowth #TechInnovation #SaaS #Freelancing
Good criteria set. One more that has earned me a lot: error cost. Automate the tasks where a missed step is expensive — lead follow-ups within a response window, data that gets entered twice — even if they're not the highest-volume ones, because the ROI shows up as fewer...
I’m currently building a RAG system for an e-commerce company, basically giving an AI assistant access to the company’s own knowledge and product information so it can give useful, context-aware responses instead of just generating random answers.
The interesting part isn’t just connecting an LLM.
It’s making sure the AI can:
→ Find the right information
→ Understand the user’s question
→ Retrieve relevant context
→ Give an accurate response
→ Actually be useful in a real business workflow
Still working on it, but I’m excited about where it’s going.
This is the kind of AI automation I enjoy building, systems that solve actual business problems, not just AI demos.
Building something similar? Let’s talk.
I’ve built something similar for Purchaser, an e-commerce marketplace for automotive and industrial products.
I built a RAG-powered AI agent inside Slack that gives the team access to Purchaser’s product and spare-parts database. Instead of opening Excel and manually searching...
🤖 Multi-Agent AI Content Generator built with n8n
I’m building an AI-powered content generation workflow that transforms a simple idea into a polished LinkedIn post using multiple specialized AI agents.
The workflow includes:
🔹 Prompt Agent — Expands the initial idea into a structured content prompt.
🔹 Creative Agent — Adds stronger angles, creativity, and engagement elements.
🔹 Master Agent — Turns the enhanced prompt into a professional, publication-ready LinkedIn post.
The key idea is simple: instead of relying on one AI agent for the entire process, each agent has a specific responsibility.
This creates a more structured, consistent, creative, and scalable content workflow.
Built with n8n + AI Agents, with room to expand the system with research, fact-checking, SEO optimization, and quality-control agents.
#AIAutomation #AIAgents #n8n #WorkflowAutomation #GenerativeAI #Automation
