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 chatbot that enables businesses to search and retrieve information from documents instantly using Retrieval-Augmented Generation (RAG).
The system processes uploaded documents, converts them into embeddings, and stores them in a vector database for fast and accurate retrieval. When a user asks a question, the chatbot fetches relevant context and generates intelligent, human-like responses.
💡 This solution helps businesses automate document search, reduce manual effort, and improve productivity.
🔥 Key Highlights:
• Real-time document querying
• Context-aware AI responses
• Fast and scalable architecture
⚙️ Built using Python, FastAPI, OpenAI, LangChain, and FAISS.
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
Designed the landing page for Smug — an AI support agent that resolves tickets, knows exactly when to escalate to a human, and has zero interest in pretending otherwise.
Most AI support tools go the humble, over-apologetic route. Smug does the opposite — the whole brand is built around a smug little cat mascot and copy like "Handled it. You're welcome." It's a genuinely fun brief: figuring out how to make confidence read as charming instead of obnoxious.
Bold electric blue and orange instead of the usual muted SaaS palette, because a product this confident shouldn't look shy about it. 💙
cool
𝐉𝐨𝐛 𝐡𝐮𝐧𝐭𝐢𝐧𝐠 𝐨𝐧 𝐡𝐚𝐫𝐝 𝐦𝐨𝐝𝐞
B2 English, based in Argentina. Payment preferably in USDT. Remote only. Quite a combination, right?
I built an AI-assisted job-search system around Freehire and Hirify. Both platforms offer official API/CLI access for automation, which makes them much easier to connect to an agent workflow. Simple Python scripts collect job listings and run the first pass of filtering against strict rules.
Then agents double-check the requirements, match them against my experience, and tailor my CV to each role. They highlight relevant projects and technologies I've actually worked with. Final review and approval stay with me.
𝐀𝐬 𝐨𝐟 𝐒𝐞𝐩𝐭𝐞𝐦𝐛𝐞𝐫 𝟐𝟔:
✅ 20 applications sent;
✅ 8 HR screenings passed;
✅ 1 video screening completed and submitted.
🚀 Technical interviews are still ahead.
I'm not ready to write off the market. Even with my constraints, things are moving.
A job search deserves 𝐚𝐧 𝐞𝐧𝐠𝐢𝐧𝐞𝐞𝐫𝐢𝐧𝐠 𝐚𝐩𝐩𝐫𝐨𝐚𝐜𝐡 𝐭𝐨𝐨: clear rules, automation, and checks on the results.
Combining CapCut with AI tools like Claude has completely changed my workflow. I use Claude to draft scripts, structure video content, and generate captions/ideas — then bring it all together visually in CapCut for fast, polished edits.
As a freelance data analyst, developer, and translator, I've started using this combo for client content too — it saves hours on planning and keeps output consistent.
Open to collaborating on video/content projects that mix AI-assisted workflows with CapCut editing. Let me know if you're working on something similar! 🚀
claude for structure then capcut for the edit is a nice split. how much time does it actually save per video?