
A Senior Developer Advocate from Mumbai, who was on an official trip and “having the time of his life”, was left shocked after returning home to find that the right side of his face had stopped working. Ali Mustafa shared his ordeal on X earlier on Twitter, detailing how he attended conferences and talked to people about artificial intelligence — something Mustafa described as “a major part of his job” and that he “loves” it.
Mustafa, who has been involved in developer advocacy and public speaking for the past 10 years, said his life took an unfortunate turn after returning to Mumbai from Singapore.
“I had to go to the emergency room because my right side started failing, especially my face. It was unresponsive and I wasn’t able to blink. I wasn’t able to do what I was able to do on my left side,” he said.
He said he had developed Bell’s palsy, a condition that usually occurs in people who suffer from infections due to extreme cold. However, he said he could not understand the reason for this condition as both Singapore and Mumbai are humid places.
Read also | AI distorts virtually everything about the economy
“So it was very unexpected, but it was revealed and it happened. Overnight I was unable to move the right side of my face. As demotivating as it was, I couldn’t talk, I couldn’t do what I love to do,” he said.
An AI tool designed for facial rehabilitation
Mustafa later created an artificial intelligence tool called “Mirror” to monitor facial reconstruction exercises after he was diagnosed with Bell’s palsy. He shared the project online and explained how the platform uses facial landmark detection and symmetry analysis to track rehabilitation progress and generate reports for physical therapists.
“But I’m a developer at heart and I love working around machine learning and artificial intelligence models,” he said while introducing the project. He added that he has previously created courses that have taught “over 500,000 students” how to get started with machine learning.
Read also | ChatGPT vs NotebookLM vs Claude: Which AI tool is best for creating PPT?
The developer explained that the condition usually lasts for weeks and that recovery is largely dependent on regular exercise. Wanting a better way to monitor improvement, he decided to combine his technical background with the recovery process.
“So I plucked up some courage, sat down at my laptop, ran a bunch of AI models and created Mirror,” he said.
According to him, the platform helps people with conditions such as Bell’s palsy perform facial exercises while also evaluating facial symmetry between the left and right sides of the face.
“It helps you do exercises and also evaluate them based on the symmetry of the left side of the face to the right side of the face,” he explained.
Tracks progress and generates reports
The tool allows users to log exercise daily and keep a journal documenting their journey to recovery. It also produces detailed reports that physiotherapists can review to provide feedback and assess progress.
The developer showed how users can revisit individual exercises, track the duration of the exercise, and even watch time-lapse recordings showing facial improvement over time.
Read also | The IMF warns that the evolving AI threat could upend financial markets
“The idea is not just to do the exercise, but to see the progress,” he said.
It uses machine learning and facial landmarks
The backend system is powered by machine learning models and uses MediaPipe facial technology. According to the creator, the model first captures a neutral facial expression before splitting the face into two parts for comparison.
The system records more than 400 facial points and analyzes the symmetry of various exercises such as eyebrow movement and smiling.
“He does that for every exercise. And at the end, he normalizes the score and then shows it to my physical therapist,” he explained.
The tool reportedly relies on nearly 478 3D facial measurements and landmarks, including eyebrow, eyelid, lip, and eyeball tracking.
Mobile access
The developer said the project was designed primarily for mobile devices, so users could easily hold their phones as a mirror while exercising.
“The model we’re using here can run on any browser and also on a mobile device. This is a mobile-first approach,” he said.
He also revealed plans to publicly deploy the project and eventually upload the code to GitHub so others with similar conditions can benefit.
“If you know of anyone who has this condition and would benefit, I’ll create a GitHub repository and also create a sample deployment,” he added.





