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
Hello everyone, this is a prototype of a B2B Marketplace that can help construction companies sell more, manage easily supplier contacts and quotes request from theirs clients, the platform can be adapted to many fields in construction starting from metal to interior home suppliers. reach me out if you think this is useful for your business so i can customize it for you 😊
Quote requests usually need a status per supplier—sent, answered, revised or expired—so buyers can compare offers in one place. Did you model each supplier’s response separately from the original request?
It's a prototype not even an mvp, i didn't build that as a complete web app to sell it, it's a prototype so those type of business can see how they can sell even to other business, and ofc database design can include a relation between, quote_demand and supplier, and in...
Got it, that makes the prototype’s scope clearer. For early validation, I’d focus the demo on how a quote moves from one request to multiple suppliers, then see whether a business owner understands the flow without explanation. Have you shown that flow to any construction suppliers yet?
Thank you. For quotes moves, it can be easily managed by keyword matching, introducing keyword selections on the quote page, and depending on what we select, the quotes will be sent to suppliers that have those keywords on theirs profiles
For showing this to construction suppliers, tried but didn't get a response for now.
Keyword tags make sense for routing. For the prototype, showing buyers why each supplier matched could make the flow easier to trust. Have you tried a short walkthrough with one supplier instead of a general pitch?
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
This is a website for my Italian client that I meet on upwork which includes a separate menu page with QR code
Printed QR codes need a URL that survives menu updates. Can the owner edit dishes and prices without generating a new code?
🚀 Introducing WanderLust — My Full-Stack Web Development Project
I built WanderLust, a full-stack booking web application using Node.js, Express.js, MongoDB, and EJS.
✨ Key features:
User authentication and authorization
Create, edit, and manage property listings
Reviews and booking functionality
Image uploads using Cloudinary
Interactive maps with Mapbox
Search and category filters
🛠️ Tech Stack: JavaScript, Node.js, Express.js, MongoDB, Mongoose, EJS, Passport.js, Cloudinary, and Mapbox.
This project helped me strengthen my backend development, database integration, authentication, and deployment skills.
I'm a junior full-stack developer interested in building useful web applications and collaborating on real-world projects.
🔗 Live Demo: https://wanderlust-tphz.onrender.com
💻 GitHub: https://github.com/Aabi-dev10/WanderLust
#FullStackDevelopment #MERNStack #JavaScript #WebDevelopment #NodeJS
did you build the reviews and booking flow first?
𝐀𝐈 𝐑𝐞𝐬𝐞𝐚𝐫𝐜𝐡 𝐈𝐧𝐭𝐞𝐥𝐥𝐢𝐠𝐞𝐧𝐜𝐞 & 𝐃𝐚𝐭𝐚 𝐐𝐮𝐞𝐫𝐲 𝐏𝐥𝐚𝐭𝐟𝐨𝐫𝐦
I built an AI-powered research intelligence platform that helps analysts and business teams query complex datasets through a single conversational interface.
𝐓𝐡𝐞 𝐏𝐫𝐨𝐛𝐥𝐞𝐦
Research teams often work across disconnected databases, reports, spreadsheets, dashboards, and documents. This slows analysis, makes cross-source searching difficult, and can reduce trust in AI-generated answers.
𝐓𝐡𝐞 𝐒𝐨𝐥𝐮𝐭𝐢𝐨𝐧
The platform combines RAG, AI agents, natural-language-to-SQL, structured and unstructured retrieval, source attribution, confidence scoring, and evaluation pipelines.
Users can ask a business question in natural language, and the system decides whether to search documents, query databases, run SQL, or combine multiple sources before returning an evidence-backed answer.
𝐀𝐜𝐜𝐮𝐫𝐚𝐜𝐲 & 𝐏𝐫𝐨𝐝𝐮𝐜𝐭 𝐄𝐱𝐩𝐞𝐫𝐢𝐞𝐧𝐜𝐞
The system evaluates answer correctness, retrieval quality, SQL accuracy, source relevance, hallucination risk, and response performance. Low-confidence results are captured for review and continuous improvement.
The frontend is built with React + TypeScript and includes AI chat, dataset exploration, source references, analytics, evaluation dashboards, and real-time updates.
𝐁𝐮𝐬𝐢𝐧𝐞𝐬𝐬 𝐕𝐚𝐥𝐮𝐞
The platform helps teams analyze data faster, reduce manual SQL work, improve trust in AI outputs, and uncover insights across multiple data sources.
𝐓𝐞𝐜𝐡 𝐒𝐭𝐚𝐜𝐤: 𝐑𝐞𝐚𝐜𝐭 • 𝐓𝐲𝐩𝐞𝐒𝐜𝐫𝐢𝐩𝐭 • 𝐏𝐲𝐭𝐡𝐨𝐧 • 𝐏𝐨𝐬𝐭𝐠𝐫𝐞𝐒𝐐𝐋 • 𝐑𝐀𝐆 • 𝐕𝐞𝐜𝐭𝐨𝐫 𝐒𝐞𝐚𝐫𝐜𝐡 • 𝐋𝐋𝐌 𝐀𝐠𝐞𝐧𝐭𝐬 • 𝐒𝐐𝐋 • 𝐀𝐏𝐈𝐬 • 𝐄𝐯𝐚𝐥 𝐏𝐢𝐩𝐞𝐥𝐢𝐧𝐞𝐬
