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
NG12 Cancer Risk Assessor
Purpose: Clinical reasoning agent that combines structured patient data with unstructured NG12 cancer guidelines to deliver risk assessments and conversational support.
Core functionality: FastAPI service exposing assessment (/assess) and chat (/chat) endpoints; uses function‑calling to fetch patient data, a shared RAG pipeline (Vertex AI embeddings + ChromaDB vector store) to ground responses in the NG12 guidelines; returns structured JSON with citations and confidence scores.
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
My hands are still slightly shaking from posting my first project yesterday, but here is build #2 before I overthink it and talk myself out of it. 😅
Meet StudyAI—an AI study companion I put together.
(Please ignore that my logged-in username is "king"—giving myself royal titles during late-night debugging sessions is my only coping mechanism as a CSE fresher).
What’s inside the update:
• AI flashcards with 3D flip animations
• PDF extraction & instant quiz generation via Gemini API
• Firebase database (which gave me multiple mini heart attacks to set up)
Month 1 of engineering has been a wild learning curve, and sharing my messy beginner progress publicly is pretty terrifying, but I'm having fun building.
Let me know what you think or what I should improve next!
Also, promise I'll change my username from "king" to my actual name... right after I figure out how to survive my first round of college exams. 💀
[Yeh I forget these, and i am sorry]---Live demo: https://flashcard-study-app-d.vercel.app/
GitHub:
flashcard-study-app-d.vercel.app
StudyAI — AI-Powered Flashcards & Quizzes
Master any subject faster. Generate intelligent flashcards and interactive quizzes from your study notes and PDFs.
🔥
I used to think the secret to better AI video was writing longer prompts.
This project changed how I approach prompting.
I took one of my actual Seedance 2.5 prompts and broke it apart. What looked like one detailed prompt was actually several different shots, camera movements,...
I built a workflow that turns a business website into a testable AI phone receptionist.
The system analyzes the website, extracts services, staff, opening hours, policies, and other relevant information, then creates an isolated voice-agent demo for that business. Instead of sending a generic recording, we can provide a real phone number that allows the business to test the agent through an actual call.
When the website or scheduling system supports an integration, the agent can check availability and book appointments during the call. Otherwise, it safely captures the caller’s details and preferred time for staff follow-up.
If a business decides to continue after the demo, the same foundation can be expanded into a production receptionist with databases, customer-specific business rules, calendar and CRM integrations, confirmations, call summaries, analytics, and administrative controls.
The extracted information can also reveal gaps in the business website. Its content and structure can then be improved so both visitors and the AI receptionist receive clearer, more reliable information.
The main lesson I share is that website extraction alone is not enough. Information must be normalized, validated, and restricted to the source material before it can be used safely in a live voice conversation.
The demonstration uses a fictional dental clinic and real recordings from my working voice-agent system. No patient data, real customer information, or invented testimonials are included.
I used Descript to assemble and refine the presentation, edit the narration and real-call sections, create captions, and prepare the final submission.
