Steady: AI-Driven Insulin & Carb Tracking
Managing diabetes is exhausting. Every meal has to be broken down into carbs, converted into insulin doses, and logged somewhere. Even small mistakes throw blood sugar off, which can throw off energy and focus for hours.
I built Steady after watching my girlfriend, Kiara, carry that mental load every day with type 1 diabetes. She’s disciplined and careful, but carb counting is still stressful. The process is repetitive, error-prone, and heavy to do alone.
That’s why I built Steady: an AI-powered MVP that makes insulin and carb tracking less of a burden.
Results and impact
The MVP gave Kiara a flow that’s quick, guided, and supportive. Instead of juggling mental math and multiple apps, she can log meals, see AI carb/insulin estimates, and store everything in one place.
Clinicians and diabetes specialists from U who reviewed the prototype also highlighted its value, especially in how it would help reduce burden, improve trust, and provide insights beyond what competing apps deliver.
One even stated they’d recommend Steady over existing options like GluRoo, calling it the “superior” tool for patients.
This means:
Less stress from guessing carb counts.
More confidence that insulin doses are in the right range.
Cleaner history of meals and doses to review with providers.
A calmer mindset, which matters as much as the numbers.
"If this becomes operational, I would be more than happy to recommend this rather than GluRoo [leading competitor] to our patients.
It would give the value that that diabetes population needs - so this would make it superior."
Katy G.
Registered Dietitian; Certified Diabetes Care and Education Specialist - University of Michigan Health
The prototyping process
After some in-depth conversation and ideation with Kiara, I jumped right into the process of building this MVP.
Step 1: Define MVP scope
Focused on meal logging, AI carb/insulin analysis, and tracking.
Designed around Kiara’s biggest friction points: accuracy and mental workload.
Step 2: Set foundations
Clear, easy-to-use, calming interface.
AI outputs explained in plain language so they felt usable, not intimidating.
Step 3: Build and design
Built in Lovable for speed.
Integrated Supabase for auth and data storage.
Connected OpenAI to handle meal analysis and creating insights.
Step 4: Test and refine
Used live with Kiara at meals to get hands-on feedback.
Met with clinicians and diabetes specialists to get expert feedback.
Iterated the UX to remove as much friction as possible.
See for yourself
Try the live prototype: Open the live Steady MVP
How to explore (takes 30 seconds):
Enter the app and click (+)
Tap Upload Meal to add a photo (or use the sample images).
See instant carb + insulin estimates.
Navigate to History to view logged meals.
Explore other tabs and features!
Important: This is an MVP demo, not medical advice. There may be bugs or placeholder content. For feedback or questions, reach out to josh@joshcanaledesign.com
What's next
More testing with a wider set of users living with diabetes, to validate accuracy and usability.
Exploring integrations with continuous glucose monitors (CGMs), nutrition databases, and wearables to make the experience more seamless.
Shaping Steady into a real product, with stronger privacy, onboarding, and personalization built in.
We have a working MVP that feels real, so the next step is pressure-testing it in daily life and expanding its reach.
Lessons for founders
A small, focused MVP is enough to test a problem meaningfully.
In health, trust and tone carry as much weight as the feature set.
Building for a real person surfaces more insights than assumptions and personas.
This project shows how quickly a focused MVP can move from an idea to something real in a person’s hands, proving impact before it ever needs to scale.
Results and impact
Clinicians and diabetes specialists who reviewed the prototype highlighted its value, especially in how it would help reduce burden, improve trust, and provide insights beyond what competing apps deliver.
Two clinicians even stated they’d recommend Steady over existing options like GluRoo, calling it the “superior” tool for patients.
This means:
Less stress from guessing carb counts.
More confidence that insulin doses are in the right range.
Cleaner history of meals and doses to review with providers.
A calmer mindset, which matters as much as the numbers.
"If this becomes operational, I would be more than happy to recommend this rather than GluRoo [leading competitor] to our patients.
It would give the value that that diabetes population needs - so this would make it superior."
Katy G.
Registered Dietitian; Certified Diabetes Care and Education Specialist - University of Michigan Health
The prototyping process
After some in-depth conversation and ideation with Kiara, I jumped right into the process of building this MVP.
Step 1: Define MVP scope
Focused on meal logging, AI carb/insulin analysis, and tracking.
Designed around Kiara’s biggest friction points: accuracy and mental workload.
Step 2: Set foundations
Clear, easy-to-use, calming interface.
AI outputs explained in plain language so they felt usable, not intimidating.
Step 3: Build and design
Built in Lovable for speed.
Integrated Supabase for auth and data storage.
Connected OpenAI to handle meal analysis and creating insights.
Step 4: Test and refine
Used live with Kiara at meals to get hands-on feedback.
Met with clinicians and diabetes specialists to get expert feedback.
Iterated the UX to remove as much friction as possible.
What's next
More testing with a wider set of users living with diabetes, to validate accuracy and usability.
Exploring integrations with continuous glucose monitors (CGMs), nutrition databases, and wearables to make the experience more seamless.
Shaping Steady into a real product, with stronger privacy, onboarding, and personalization built in.
We have a working MVP that feels real, so the next step is pressure-testing it in daily life and expanding its reach.
Lessons for founders
A small, focused MVP is enough to test a problem meaningfully.
In health, trust and tone carry as much weight as the feature set.
Building for a real person surfaces more insights than assumptions and personas.
This project shows how quickly a focused MVP can move from an idea to something real in a person’s hands, proving impact before it ever needs to scale.
See for yourself
Try the live prototype: Open the live Steady MVP
How to explore (takes 30 seconds):
Enter the app and click (+)
Tap Upload Meal to add a photo (or use the sample images).
See instant carb + insulin estimates.
Navigate to History to view logged meals.
Explore other tabs and features!
Important: This is an MVP demo, not medical advice. There may be bugs or placeholder content. For feedback or questions, reach out to josh@joshcanaledesign.com
Steady: AI-Driven Insulin & Carb Tracking
Industy
Digital Health
Stack
Lovable, Supabase, OpenAI integration
Steady: AI-Driven Insulin & Carb Tracking
Industy
Digital Health / Diabetes Management
Stack
Lovable, Supabase, OpenAI integration