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
AI-Powered Fitness Instructor Generator (ML + NLP)
AI-powered fitness app built with Streamlit, NLP models, and ML-based goal prediction.
Generates personalized workout plans with live timers, exercise videos, and optional voice guidance.
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
Claude
Claude has entered the design space. How are you using it?
Contra University
Learn from expert creatives how to earn more using next-gen AI tools.
Brand Design
The best brand designers are on Contra. Scroll to see what's trending in brand design. What are you building?
creativeaiflow
Creative AI workflows are evolving. What tools do you use, and what are their strengths and weaknesses?
freelancerlife
Freelancer life is wins, pivots, and everything in between. What’s yours right now?
Related posts
Talkinator- a reimagined translator app.
Even though I'm no immigrant, I forget words like it's my full time job.
LIVE PROJECT
FLOWSTEP
PS: While building the app, my major pointers were:
1) We all forget words and when we do remember them after forcing our brain, it feels like a weight lifted off.
→ This app is supposed to make that feeling easily attainable. 2) Translators should be capable of doing more.....
The simulation is where the practice happens.
You've seen the profile, you know what this person needs, now you get to rehearse the conversation before having it for real.
The AI generates responses based on everything it knows about this teammate, personality, history, how they tend to react.
A timer keeps the session focused. When you're done, you get instant feedback: Did you make the objective clear? Did you discuss next steps?
The design choice here was to close the loop fast. Practice, feedback, adjust. Skip waiting or lengthy reports, instead only a quick summary that tells you what landed and what didn't so you can go again or exit the scenario in the SaaS AI coaching platform.
woah 😮
Here's our submission for the #flowstepchallenge :
"Let me cook" - app that turns following a recipe into a game you play one step at a time. We made this for people who are short on time, energy, and confidence with cooking, and a little sick of takeout.
The idea is simple: You cook one dish, step by step, and get scored as you go. Not on speed, but on timing and presence.
The bonus part we built here :
One doesn't cook from a shopping list. Just point the camera at whatever's already in the fridge, be it two eggs, an onion, some leftover rice and the app builds a dish around that! It works from what one have, not what one needs to go buy. Which is exactly how (from personal experience) one actually stands in the kitchen at 8pm wondering what to make.
We had a lot of fun bringing this idea to life on the Flowstep AI builder. Our workflow started with stress-testing the idea in Claude, prompting in Flowstep, refining in Figma and deploying a testable MVP!
We deployed the MVP via Expo Go to test on mobile phones. See below, the app walkthrough and also us testing it on a phone to see how it works! The test resulted in a successful dish too. 🔥
Would love to know your thoughts on this project! Should we deploy this for testing further? 👀
