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
Building an AI-powered SOC & Incident Response Platform using Elasticsearch, FastAPI, and real-time security alert pipelines.
Developing automated incident ingestion, normalization, enrichment, and attack visualization systems for modern security operations.
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
AI-Powered Customer Support Hub (n8n + Gemini + Notio
built a fully automated customer support system that streamlines communication and data management. By integrating Gmail, Gemini AI, and Notion, the system automatically processes incoming emails, analyzes sentiment, and categorizes them into a structured Notion database.
Key Features:
• Automated Parsing: Extracts key information from emails using AI.
• Sentiment Analysis: Categorizes inquiries based on tone (Positive/Negative/Urgent).
• Smart Drafting: Generates initial AI-powered draft responses to speed up support time.
• Centralized Database: Organizes everything into 7 specific categories in Notion for easy tracking.
Tools Used:
• n8n (Workflow Automation)
• Notion (Database & CRM)
• Gemini AI (Natural Language Processing)
• Gmail API
CasePrepAI: Insurance Case Management System
CasePrepAI was a workflow simplification and operational clarity project disguised as an AI product.
The core problem was not the lack of features, it was the amount of cognitive overload insurance teams faced while handling complex case preparation workflows across fragmented systems, documents, communication channels, and repetitive manual processes.
Most insurance workflows are operationally dense. Teams spend significant time gathering information, reviewing case details, organizing documentation, and preparing reports across tools that were never designed to work together cohesively.
My role was to rethink how AI could reduce operational friction without disrupting critical human decision-making.
Instead of designing AI as a standalone assistant, I approached the platform as a collaborative workflow system:
What tasks are repetitive?
Where do users lose time?
Which decisions require confidence and visibility?
What should AI automate versus support?
This led to a more structured, AI-assisted experience focused on speed, clarity, and workflow continuity.
I redesigned the information architecture to better support high-volume case management, simplified complex navigation paths, and introduced interaction patterns that made large datasets and case histories easier to scan, prioritize, and act on.
One of the key judgment calls was intentionally reducing unnecessary AI exposure across the product. In industries like insurance, trust and clarity matter more than novelty. Rather than forcing conversational AI into every workflow, I focused on embedding intelligence contextually where it improved efficiency, summarization, recommendations, and preparation speed.
The result was a platform direction that felt less like a traditional enterprise tool and more like an intelligent operational workspace designed around how insurance teams actually prepare, review, and manage cases under pressure.
More importantly, the project demonstrated my approach to product design:
I simplify complex systems, align AI with real user workflows, and design products that improve operational decision-making, not just visual interfaces.
Built an AI Security Scanner for GitHub Orgs in 2 Weeks
Engineered an end-to-end AI platform that scans entire GitHub organizations for vulnerabilities and auto-generates fix PRs.
What it does:
Crawls 100+ repos via GitHub GraphQL API in batch mode
Runs GPT-4 over real source code to detect SQL injection, XSS, hardcoded secrets, CSRF, auth bypasses
Scores by severity, generates secure code fixes, creates PRs automatically
Real-time WebSocket dashboard shows live progress
Tech: Next.js 15 · Node.js · Supabase · BullMQ · Redis · OpenAI · CrewAI
Open source, MIT licensed: github.com/aymandakir/org-code-ai
Shipped in under 2 weeks. Full stack, production-ready.
Great work! And it's open source too. 😄
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?