DEV Community: Shraddha Nigam

Pose Coach 📸 — What If Your Camera Could Teach You How to Pose?

Shraddha Nigam — Sun, 25 Oct 2026 17:26:56 +0000

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady

Have you ever asked someone to take your photo, only to find out that you look awkward in every single shot? 😅

Or tried recreating a pose from Instagram, taken 15 pictures, and still wondered why none of them looked quite right?

Sometimes, the hardest part of taking a photo isn't the camera. It's knowing where to stand, how to pose, and how to frame yourself.

That's the problem I wanted to solve.

Meet Pose Coach — your personal AI photography director. 📸

The idea is simple: what if your phone didn't just capture the moment, but actually helped you get ready for it?

What I Built

Pose Coach is a mobile-first photography assistant designed to help people pose confidently and take better photos without needing someone else behind the camera.

Instead of guessing where to stand or repeatedly retaking pictures, the goal is to let your phone guide you in real time.

✨ The experience I'm building

📷 Smart framing: Help users understand whether they need to move closer, step back, or adjust their position in the frame.
🕺 Pose guidance: Use a reference pose to help users understand body alignment and positioning.
👗 Traditional poses: Explore pose ideas for sarees, lehengas, kurtas, and other ethnic outfits.
🧥 Western poses: Discover casual, fashion, street-style, and portrait poses.
🤳 Selfie mode: Get help with face positioning, angles, and composition.
🫶 Couple photography: Explore two-person poses and improve spacing and framing.
🔒 Privacy-first AI: Build around on-device computer vision so personal camera footage doesn't need to be uploaded to a cloud service.

The project currently has a mobile-first interface, camera experience, and pose categories. The more advanced live AI coaching and pose-matching experience is still being developed and tested.

My goal is to make taking a good photo less about trial and error and more about confidence.

Code

💻 GitHub repository: ShraddhaNigam19/pose-coach

The project is built with a mobile-first web approach, using React and TypeScript.

I'm building the application around a practical combination of on-device computer vision and photography-specific logic, rather than relying on a chatbot to tell users generic posing tips.

Feel free to explore the repository and share suggestions or improvements!

How I Built It

The most interesting part of Pose Coach isn't the interface. It's the idea of turning what a camera sees into useful, understandable instructions.

The technology behind it

React + TypeScript + Vite: Application structure and mobile-first UI.
MediaPipe Pose Landmarker: The intended open-source computer vision foundation for detecting human body landmarks.
@mediapipe/tasks-vision: Browser-based pose estimation.
Camera API: Accessing the camera and capturing photos.
Canvas overlays: Rendering pose references, detected landmarks, and framing guides.
Framing engine: TypeScript geometry and rules that translate landmark positions into practical feedback.
Local persistence: Saving preferences and favorite poses on the device.

The challenge: from landmarks to useful guidance

A pose model can estimate where body landmarks are located, but raw coordinates don't tell someone what to do next.

Imagine selecting a full-body pose while your feet are outside the camera frame.

Pose Coach should recognize that the composition doesn't meet the selected framing target and tell you to step back.

Or imagine trying to match a reference pose. Instead of placing a static stick figure over the camera and calling it AI, the application should distinguish the target pose from the user's detected skeleton, compare their alignment, and suggest meaningful corrections.

That's the engineering challenge I'm most interested in: turning computer vision into practical, real-time coaching.

Why Does Open Innovation Matter?

I want Pose Coach to be useful without requiring users to pay for a proprietary AI API every time they open their camera.

Open-source AI makes it possible to experiment with local inference, inspect the underlying implementation, adapt the processing pipeline, and build a privacy-conscious experience.

With an appropriate on-device model, camera frames can be processed locally instead of being sent to a remote AI service. That can also reduce network dependency and avoid per-request inference costs.

It gives developers room to improve the product in ways that matter to the application: better landmark handling, more useful framing rules, alternative models, and improved performance on mobile devices.

Of course, open-source doesn't automatically mean every model is lightweight, offline-ready, or licensed for every use. Model assets, runtime compatibility, licensing, and real-device performance all need to be verified.

For me, open innovation is about having the freedom to understand the technology, adapt it, and build something useful around it.

My Agent Session

I used an AI coding assistant during development to help implement and refine the application.

DevRelay session: Add your session link here if available.

I also learned that getting a polished interface on screen is only one part of building an AI product. The underlying model must work, its output must be reliable, and the features must respond to real input.

That's why I'm focusing on making the AI functionality genuinely useful instead of treating the model as a decorative add-on.

The Lazy Payoff 🦥

Imagine setting up your phone for a full-body photograph.

You take a picture. Your feet are cropped out.

You move the phone. Now there's too much empty space above your head.

You try again. Your pose still doesn't look right.

We've all been there. 😅

Pose Coach aims to reduce that cycle by guiding the user before they press the shutter.

The payoff I'm working toward is simple:

Less trial and error. Fewer retakes. More photos worth keeping.

I haven't measured the time saved yet, so I won't claim a specific improvement. My next milestone is to test the live framing workflow on real mobile devices and compare the experience with taking photos without guidance.

One Last Thought 💭

I started with a simple question:

What if your phone could be your personal photography director?

A camera that helps you find the right position, understand your pose, and feel more confident in front of the lens.

That's the experience I want Pose Coach to deliver.

I'd love to hear from the community:

If your camera could give you one instruction before taking a photo, what would you want it to say?

Would it be "move back," "fix your posture," "try a different angle," or something else entirely?

Let's build more useful things with open-source AI.

devchallenge #hf26challenge #opensource #AI #ComputerVision #React #Hacktoberfest

What If Our Desktop Had Its Own Little AI Companion? Meet Luna

Shraddha Nigam — Sat, 10 Oct 2026 15:27:15 +0000

This is a submission for the MLH x DEV Writing Challenge

Meet Luna 🐱

What I Built

My husband and I have always liked those little animated desktop pets — the tiny characters that move around your screen and make your computer feel a little more alive.

One day, we started talking about them and wondered: What if we could make something like that, but instead of just moving around the screen, it could actually help us?

Imagine having a little companion on your desktop that you could ask questions, give tasks to, or turn to whenever you needed something — without constantly switching between browser tabs and different applications.

That conversation became the idea behind Luna.

Luna is an AI desktop companion that lives on your screen and gives you a more natural way to interact with AI. The idea is simple: instead of always going to AI, bring AI closer to where you already work.

From an Idea to a Project

When I started building Luna, I wanted to bring together two things: the fun of having an animated desktop pet and the usefulness of an AI assistant.

I built it using Electron, React, and TypeScript, with Gemma, Google's open-weight AI model family, powering its AI experience.

Electron made it possible to create a desktop application, while React and TypeScript helped me build the interface and manage the application logic. I integrated Gemma through Google's GenAI tooling to let users interact with AI through Luna's chat interface.

But turning the idea into something real was definitely not as simple as imagining it!

Getting separate desktop windows to communicate, making sure messages reached the right place, and handling AI responses reliably took plenty of debugging. Sometimes, fixing one thing led to another problem, and I had to go back and figure out what was happening.

Those moments were frustrating, but they also taught me a lot. I realised that building a useful AI product isn't just about the model. The interaction, the interface, and all the little details matter just as much.

Why Gemma?

I wanted to explore how Gemma could be used in a real desktop application rather than just another chatbot interface.

For me, the interesting part was bringing an AI model into an experience that already feels familiar. We are used to opening websites and typing into chat boxes, but what if interacting with AI could feel more like talking to a little companion that is already there?

That's the direction I wanted to explore with Luna.

What's Next for Luna?

Luna is still a work in progress, and there is a lot I want to improve.

I'd love to make the companion feel more alive, improve its everyday interactions, and explore features that help it understand what's happening on the screen and assist with tasks more naturally.

The bigger idea is to make Luna more than a cute character on the desktop. I want it to become something genuinely useful — a companion that combines personality with practical AI assistance.

What I Learned

This project reminded me that interesting ideas don't always start with a big technical problem. Sometimes, they start with something small that you enjoy and a simple question: What if?

For us, that question came from watching animated desktop pets. For me, it turned into an opportunity to learn more about Electron, desktop application development, AI integration, and the challenges of bringing different pieces together into one experience.

And honestly, seeing the idea become a real project has been one of the most satisfying parts of the journey.

I'm excited to keep building Luna and see where this idea goes next. 🐱

Demo

💻 Explore the source code: https://github.com/ShraddhaNigam19/AI-Companion

I'd love to know: If you could have a little AI companion living on your desktop, what would you want it to do?