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
Built an AI-powered web scraping and data enrichment pipeline using Apify and Bright Data for scalable extraction from protected websites. Integrated AI agents to parse raw content, classify data, and automate decision-based workflows. Developed API integrations, webhooks, and async processing for reliable data flow between services. Stored and managed structured data in Supabase (PostgreSQL), including normalization and synchronization for downstream systems. Optimized proxy usage, retries, and task handling for stability and cost efficiency.
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
Built this AI agent to find, organize, and manage leads through Gmail, helping automate lead handling and outreach.
n8n is absolute gold for orchestrating lead pipelines like this! Connecting Gmail parsing with LLM qualification saves teams dozens of hours weekly. As someone who builds custom agentic lead automation workflows, seeing clean visual architectures like this is super satisfying. Top-tier build, Talha!.
Another late night. Building a quant trading system an agentic model where different AI agents handle research, testing and risk, and none of them is allowed to place a trade on its own.
The hardest part so far? Being honest when the results say "not yet." Most strategies I've tested failed once real costs were included. That's exactly what testing is for.
Keeping The Psychology of Money and The Diary of a CEO close while I figure it out. What are you reading these days?
Curious how you’ve separated the agents from execution. When you say none can place a trade on its own, is that enforced through a separate execution service with fixed risk checks, human approval or both? I’d love to understand where the agent's decision-making ends and the hard rules take over.
I designed and built an enterprise AI automation system using n8n, AI agents, RAG, Redis, and PostgreSQL to automate complex business workflows, improve decision-making, and create scalable AI-powered operations.
The system uses n8n as the automation orchestration layer, where incoming business events trigger workflows that route tasks to specialized AI agents. A RAG pipeline retrieves relevant knowledge from business data sources, allowing AI agents to generate accurate, context-aware responses and decisions. Redis handles queue-based processing for high-volume tasks, while PostgreSQL stores structured data, workflow history, and audit records.
The automation architecture connects multiple technologies including n8n, OpenAI API, AI Agents, RAG pipelines, Vector Databases, Redis, PostgreSQL, APIs, Webhooks, Slack integrations, Docker, and Python services to create reliable enterprise workflows.
The solution helps businesses reduce manual operations, automate repetitive processes, improve response times, maintain better data accuracy, and scale AI workflows securely. It includes monitoring, validation, error handling, and human approval flows to ensure reliable production usage.
Tech Stack: n8n, OpenAI, AI Agents, RAG, LangChain, Redis, PostgreSQL, Qdrant, Python, FastAPI, Docker, APIs, Webhooks, Slack.
