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
TypeSafe AI: Deterministic Agent Runtimes & Structured LLM Decisions. Transforming natural language into strictly-typed primitives and state-machine transitions with zero hallucinations. Built in TypeScript & Python. #AIEngineering #TypeScript #Python #LLM #Automation
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
Challenges
View all
Related posts
Honestly, just too much baggage to carry
Hello, Contra community!
I’m Farooq Hasan, an AI Automation and Data Analytics specialist helping businesses transform raw data and repetitive processes into clear insights and efficient solutions.
I work with Power BI, SQL, Python, Excel, DAX, Power Query, FastAPI and PostgreSQL to create:
• Interactive dashboards and business reports
• Data cleaning, analysis and visualisation
• Workflow and task automation
• AI-assisted tools and web applications
My portfolio includes a deployed AI job-workflow platform and analytics dashboards covering sales, restaurants and human resources.
I’m currently available for freelance projects and would be pleased to collaborate with businesses that value accuracy, clear communication and dependable delivery. Feel free to message me to discuss your requirements.
I built ReviewIQ because technical interviews don't always test whether you can actually review code.
ReviewIQ is an AI-powered code review interview trainer built for software engineers.
You pick a role, language, and seniority, then get a realistic PR diff with bugs intentionally planted in it.
You write your review.
Then the system grades it against the actual bugs, shows what you caught, what you missed, and gives you feedback on how a stronger reviewer would approach it.
The interesting part was building the grading system so it isn't just "AI thinks your answer is good." The bugs have a known ground truth, so the review can be evaluated against something concrete.
Built with Next.js, Supabase, PostgreSQL, OpenAI, and Lemon Squeezy.
I'm interested in building more products where AI isn't just a chat box, but an actual part of the product experience.
The known-ground-truth approach is a great product decision—it makes the feedback feel earned rather than like an opaque AI verdict. I also like that the flow tests the actual review skill instead of rewarding pattern-matching in interviews.