AI AutomationSoftware
Athliix: Turn Every Workout into a Challenge
Turns every workout into a challenge, with AI-scored activity verification.
DisciplinesAI Automation · Software
Our roleDesign, build, release
Technologies
Python
PyTorchVision modelsInference at edge
React
Node.js
PythonPyTorchVision modelsInference at edgeReactNode.js
Athliix
The challenge
What was in the way.
Athliix needed ai automation and software work delivered as one system rather than split across vendors — turns every workout into a challenge, with AI-scored activity verification.
Disciplines in scope
Hardware—
Firmware / IoT—
AI / MLIn scope
Web & mobileIn scope
How we built it.
We restated the brief as constraints — power, latency, cost, compliance — and named the ones that conflicted. A working slice through the riskiest layer was signed off first, then built out in two-week increments with one demo each, reviewed against the same engineering standard across hardware and software.
01Technical discovery
02Architecture & prototype
03Build & iterate
04Deploy & hand over
One team accountable for the whole stack, not a slice of it
A working prototype before the roadmap was fixed
Performance and reliability held to spec under real load
A handover the client's own team could carry forward
01Shipped
Delivered to production and still maintained by the team that built it.02Tested
One test matrix across hardware, firmware and interface — no gaps between layers.03Documented
Runbooks, monitoring and escalation handed over with the system.04Scaled
Grew with usage without re-architecture or a second rebuild.