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
AXIOM — AI-Powered Assistant Platform
AXIOM is a modern AI assistant platform inspired by the experience of ChatGPT, designed with a clean, premium, and intuitive interface. I built the platform with a focus on smooth conversations, modern UI/UX, and an engaging user experience.
The project includes AI-powered conversations, chat history, project/workspace organization, AI agents, research capabilities, and image-generation features. It also includes user authentication and a responsive interface designed to work seamlessly across desktop and mobile devices.
Key Features:
AI-powered conversational assistant
Modern ChatGPT-style interface
Chat history and organized conversations
Projects and AI Agents
Research functionality
AI image generation
User authentication
Responsive and interactive UI
Premium modern dashboard experience
AXIOM demonstrates my ability to design and develop complex AI-powered web applications with modern frontend architecture, interactive interfaces, and scalable functionality.
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
My AI assistant runs all day. The expensive model only does the thinking.
Most requests need no AI at all. "Call me in 30 minutes" is handled by plain code. Reminders, schedules and limits are code too.
Short tasks like sorting and scoring go to fast models on a free tier.
The big model only gets planning and long conversations, where it actually has to think.
If it hits a limit, a backup model answers instead of the app going silent.
If your AI app's bill keeps growing, check what really needs the big model.
What does your app send to the most expensive model?
Same pattern holds in outbound tooling. Filtering, dedupe and enrichment lookups are plain code. The model only writes the first line once the row is already verified. Cuts cost and the weird outputs.
✨Two creative directions. One product.
Which AI-generated visual do you love more Version 1 or Version 2?
Your opinion matters! Let me know your favorite in the comments👇🏻
2 voted
40%
3 voted
60%
5 votes
Closed
Version 1 is really stunning great job Mary 🎉🎉🔥🔥
CRAG — Self-Correcting Research Assistant
Overview
A research-assistant project exploring how AI applications can retrieve information and improve the quality of their responses through a self-correction workflow.
Project focus
Python-based AI application development.
Retrieval and research workflow design.
Improving answer reliability through evaluation and correction.
Technologies: Python, AI, retrieval-augmented generation.
Self correction is where RAG gets useful. How do you judge a retrieved chunk as bad enough to trigger a new search?