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
RAG Chatbot that answers straight from your own documents, with sources you can check. Built on a Qdrant vector store with FastAPI and LangChain. The trick to accuracy is retrieval, not the model: get what's pulled in right and it stops making things up. Stack: Python, FastAPI, LangChain, Qdrant, Next.js.
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
Trending
retrofuturism
Share your favorite designs from the past exploring the distant future. Or your own take on the aesthetic 🚀
halftone
Dots. Texture. Grain. Let's see your designs using the halftone technique.
Midjourney
Creatives are showing off what they're making with Midjourney.
colorgrade
Video editors sound off: How do you enhance the mood of your video in color grading?
Related posts
Creating a website for my own business was super fun.
caparica.love is my side hustle, which I started around 4 months ago.
It's all about organizing romantic events, from proposals on the beach to romantic picnics.
Something about this website I like the most is the "Book Now" button, which allows my clients to choose the experience by themselves, without me being involved.
Another useful thing is the AI Assistant. It can consult my customers on its own, providing them with detailed information.
Try out the AI Assistant on the website and let me know how it went!
😍 I love this work 🔥
Personal finance dashboard — from an hour of admin to two minutes
A weekly household finance workflow (manually pulling bank CSVs, splitting and categorising spends across two people, cross-checking shared expenses, reviewing totals against savings goals) was taking about an hour every week and still made it hard to tell at a glance whether spending was on track. Designed and built a dashboard that automates the pull, categorisation, and monthly view.
My role:
Research (mapped the existing manual workflow and pain points), UX design, and AI-assisted build of the dashboard.
Outcome:
Cut the weekly admin task from roughly an hour to about two minutes.
Note on scope:
Personal side project, not a client engagement. Included here as a live example of the kind of workflow-to-dashboard problem I take on for clients (repeat-purchase and admin-heavy flows, see Pet Circle and SafetyCulture project cards).
Project details up on my profile.
This sounds like a game-changer for weekly finances! How did you automate the CSV pulls?
Currently building autonomous AI systems that actually survive production — not just the demo.
Most AI projects work beautifully in a controlled test and then quietly fall apart on real data, edge cases, and concurrency. I focus on the unglamorous engineering that closes that gap: data validation pipelines, boundary checks, error handling, and knowing exactly where deterministic logic should own the decision instead of the model.
Recent work includes agentic workflows built with Python and FastAPI, an LLM reasoning layer for the genuinely ambiguous decisions, and automation orchestrated through Make with MCP. My background is technical support and operations, which means I design for the failure case first — I've spent years watching systems break in ways their builders never anticipated.
If you have an AI pilot that impressed everyone in the demo and then stalled on the way to something dependable, that gap is exactly what I build for.
Open to Applied AI / AI automation projects.
Keep it up!