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
A wholesale business was managing stock, customer ledgers, and profitability across disconnected spreadsheets. I built a production inventory and accounting system that now supports its daily operations, then added an agentic AI assistant for natural-language business intelligence.
I developed a custom MCP server that gives Claude secure access to the live database. The owner can ask about stock levels, sales trends, customer balances, or profit by product and receive answers grounded in actual business data, without manually building reports.
The system includes the complete order and inventory lifecycle, transaction ledgers, automated financial reporting, and a Claude-powered AI assistant connected through MCP. It brings operations, financial data, and real-time insights into one practical business platform.
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
🔥 New addition to my portfolio 🔥
Previously I had an SVG mask of my logo in the center with my showreel behind it, but this had a couple of issues. So yesterday I pushed it further and I created a 3D variation, video playing inside it, glass refraction and it's even more beautiful when you click into it.
Take a look; www.grilledpixels.com
the glass refraction on the 3d mark is a cool touch. did you build the interaction with three.js?
Bridge — Helps conversation coaches eliminate hours of manual qualification by turning emotional inquiries into confirmed, fully prepared bookings.
Video: User flow and the professional Dashboard.
great work!!
An experimental AI-agent application for researching business opportunities using web search, webpage extraction, evidence collection and structured analysis.
The evidence collection step is where I would look first. When two pages disagree, do you keep both source links so someone can see why the analysis chose one?