Huddl
03/06/2026
We've made an exciting breakthrough in developing an algorithm capable of assessing the AFL drop punt skill.
We've successfully integrated hand landmark detection and object detection into our architecture, enabling our system to simultaneously track 21 hand landmarks per hand and read ball orientation, descent path, and contact geometry.
This means Huddl can now assess not just where the body is, but how the hands interact with the ball at every phase of the skill, bringing a level of detail that hasn't been available to PE teachers before.
Our algorithm analyses 11 biomechanical metrics across four assessed phases, with every measurement expressed as a computable value derived from landmark coordinates. Items like the grip axis angle, bilateral symmetry ratio, channel maintenance, orientation stability during descent, ball orientation at release, contact zone index and knee drive during follow through. All metrics are research-backed and grounded in Fitts and Posner's 3 stage model of motor skill acquisition, ensuring every benchmark reflects what is biomechanically achievable and developmentally appropriate for the student.
An important note is that our benchmarks are not fixed. They adapt across five developmental year bands from Pre-Primary through to Year 10. Through our research, we recognised the nuanced patterns of movement relevant to each age band. A PP student will not be capable of demonstrating a controlled 1 handed guide & release in the same capacity as a grade 10 student. Therefore, we reviewed every metric across each year band to ensure they were age appropriate, educationally relevant & research informed.
We've also built the capacity to detect and account for every meaningful variation in how a student might attempt the skill across key developmental stages. From pattern-classified release errors like the toss, slam, lateral drop, and compressed release, to contact errors including toe contact, heel contact, and outside-of-foot contact, through to grip errors such as hands positioned too high or too low on the ball. More than 40 variations were identified, classified, and fed into the algorithm.
The result for teachers is a model capable of not only grading the skill but providing highly accurate, phase-by-phase diagnostic feedback that tells them exactly what they need to move every student forward.
What do you think? Could you see yourself using this in your school?
www.huddlapp.com.au
19/05/2026
Are we assessing the outcome of movement? Or are we assessing the quality of movement? 🏃♂️
In this article I dig into the science of biomechanics and kinematic data to make the case that fast doesn't always mean good and that the students who look fine on the stopwatch are sometimes the ones who need our attention the most.
👉 https://www.huddlapp.com.au/news/fastest-student-might-be-your-worst-runner
14/05/2026
Founder update.
We've learned a lot over these past few weeks. Building and launching an assessment tool with new technology is a real challenge, but I'm pleased to report we've made excellent progress. We identified a number of issues that needed fixing before we could launch our beta.
Getting it right matters more to us than getting it out fast. Teachers are trusting us with their students and their professional assessment practice... That's not something that we take lightly.
This weekend we're meeting to do our final review and flight test. If everything goes to plan, beta schools will have access within the next couple of weeks.
To every school that's been waiting patiently, thank you. We're nearly there.
www.huddlapp.com.au
11/05/2026
Today I had the pleasure of sitting down with Dr. Shane Pill, one of Australia's leading voices in Physical Education research and coach education.
We discussed our platform - how it works, its capabilities and use cases around the world. Its fair to say Shane was excited by the technology & looks forward to seeing where it takes us.
I'm incredibly grateful for his time, honesty, and generosity in connecting us with his colleagues at Flinders University.
www.huddlapp.com.au
07/05/2026
Today we filed a patent application with IP Australia to protect Huddl's assessment methodology. It's something we've been working toward for a while and filing it feels like an important step in building something that's genuinely worth protecting. We're excited about the journey ahead!
04/05/2026
Next week, we're sitting down with the man himself - Dr. Shane Pill, to chat about the future of assessment in Physical Education. We're excited & looking forward to sharing what comes from it.
30/04/2026
With the beta test program right around the corner, now is the time to speak with admin about using Huddl in your school.
To facilitate these conversations, we've prepared a School Info Pack that provides all the info principals need to know - how the app works, what data is stored, privacy compliance, and how to get started. It includes a consent form that you can provide to parents with the key info they need to know.
Download it here:
www.huddlapp.com.au
28/04/2026
Looking for an exciting PD idea?
We're offering free one-hour workshops for WA schools & we'd love to come to your school. We'll show your PE staff how Huddl works, get a hands on with Skill Grader & how it can transform the way your school assesses movement.
Interested? Drop us a message or email: [email protected]
20/04/2026
This morning I was invited to present to Kane Lucas and the amazing staff from the RASSA network.
Walking into a room full of PE teachers who genuinely care about the quality of their practice is something special & one I won't forget. These are exactly the type of people we built Huddl for. Educators who think deeply & care about how their students move.
I'm very grateful to Kane for the opportunity and to everyone who gave up part of their morning to hear what we're working on. The questions, the feedback & the conversation afterwards.. That's the stuff that reminds me why we started.
Recently, we made a big decision to change how Skill Grader works.
Early on, we assessed movement in real time, which basically meant we mapped a digital skeleton over students as they moved during recording. In theory, it looked transformative.
But in practice, we found that it created many issues.
Real-time grading struggles with accuracy. Our system would occasionally lock onto objects in the background, lose track of limbs through occlusion, or miss parts of the movement altogether. On older devices, it could even cause freezing.
Most importantly, it wasn’t giving us the level of consistency we expected from an assessment tool.
We knew that if Skill Grader wasn't accurate the first time, it wastes everyone's time.
So we made the product decision to move Skill Grader to post-assessment.
Now teachers record the movement first. Skill Grader then processes the footage, plays it back with the skeleton overlaid, and delivers results alongside the clip.
That single change improved grading accuracy by up to 40% — a difference that genuinely matters when grades are being assigned. Our skeletons track key joints far more accurately & free from occlusion. Biomechanical measurements are far more consistent.
The level of detail and consistency we can achieve this way simply isn't possible in real time.
It was a harder technical path — but it was the right one for the real contexts we experience as PE teachers.
Click here to claim your Sponsored Listing.
Category
Website
Address
Perth, WA