DevFest Montréal 2026

← Back to the programme
4-4 · Under PressureEnglish

Off the Edge: Grading Google AI Edge and Gemini Against a Practitioner's Eye

Category
AI & ML
Format
Session — 40 minutes
Audience level
Intermediate

𝗔𝗜 𝗮𝗹𝗿𝗲𝗮𝗱𝘆 𝗵𝗲𝗹𝗽𝘀 𝘂𝘀 𝗹𝗲𝗮𝗿𝗻, 𝘄𝗿𝗶𝘁𝗲 𝗮𝗻𝗱 𝗱𝗲𝗰𝗶𝗱𝗲. 𝗖𝗮𝗻 𝗶𝘁 𝗵𝗲𝗹𝗽 𝘂𝘀 𝗺𝗼𝘃𝗲 𝗯𝗲𝘁𝘁𝗲𝗿? Getting better at a physical skill takes someone who can see what you cannot: your own body in motion. That asks a machine to understand space rather than words, then say something worth acting on. This talk asks how far that has come, using an application built for the purpose and a sport where the answer can be checked: jumping rope. Someone who practises it can grade the answer, so the model gets no benefit of the doubt. It runs on Google Cloud. Google AI Edge's Pose Landmarker measures the body. Gemini video understanding is asked for the harder thing: not a description of the video, but advice that changes the next session. How far does a pose model go on real footage, when the object this sport is built around fills 0.058 % of the picture and blurs in every frame? Is Gemini genuinely useful as a coach, or only convincing? And when the measurement and the advice disagree, which one do you believe? We walk the whole route, run the app live on real sessions, and close with what practitioners made of the coaching and a grade for each.

Speakers

Boris-Wilfried Nyasse

Founder · Oloodi

Founder of 𝗢𝗹𝗼𝗼𝗱𝗶 𝗧𝗲𝗰𝗵𝗻𝗼𝗹𝗼𝗴𝗶𝗲𝘀, a cloud-native AI product studio. We build our own products across legaltech, HR tech, and fintech, and we help other founders take theirs from prototype to production on Google Cloud. I am a 𝗚𝗼𝗼𝗴𝗹𝗲 𝗗𝗲𝘃𝗲𝗹𝗼𝗽𝗲𝗿 𝗘𝘅𝗽𝗲𝗿𝘁, and I have spent more than a decade in software engineering, most of it close to Google Cloud, leading teams through migrations to new architectures. What interests me is the gap between what a technology promises and what it actually changes in the daily work of a company. Closing that gap is most of the job, and it is rarely the part that gets demoed. I speak at conferences and mentor developers, and I prefer sessions that report what actually happened over sessions that show what could.