- MLOps North
- Toronto Summit
- Presented by TMLS
Coding Agents & Dev Workflows
About the track
This track is for senior and mid-level engineers putting models into production, with legacy codebases, token budgets that aren’t unlimited, and a healthy skepticism of the hype.
We’ll cover;
- Coding agents on complex codebases, legacy systems, and rebuilds
- The code review bottleneck when agents write faster than teams can review, and the review gates and decision trails that hold
- Secure AI-assisted development. How top-performing teams treat credentials, dependencies, permissions, and what agent-written code must pass before it merges.
- AI-assisted MLOps, meaning infrastructure, architecture, and ops work, not just application code
- You’ll leave knowing where your own practice sits against the top percentile, and the specific things to change to close the gap so you can embrace this new era of development.
Track host
Founder TMLS, MLOps World
See Track Lead Profile
Graham is a recognized expert in databases, artificial intelligence, distributed systems, and computational linguistics, specializing in developing complex distributed systems and Cloud/IoT technologies at the scale of hundreds of millions of users, thousands of nodes.
As a leader, he has held a range of critical roles over the last 30 years, most recently helping to lead Wattpad to a successful exit.
As a technologist, Graham has led teams to many patents and papers, all the while transitioning breakthrough research into innovative products, and holds a number of patents himself in these areas.
He has also been a leadership coach for over a decade, and maintains an unshakeable belief in people – in particular, growing and nurturing high performing, inclusive teams and leaders.
Graham holds a BMath in Computer Science and Software Engineering from the University of Waterloo.
Sessions in this track
Friday, November 6th | 10:55 AM – 11:40 AM
How to Not Be Wrong About AI
Consultant,
Third Bit
Thursday, November 5th | 2:55 PM – 3:25 PM
Spec-Driven PBT: Deriving Semantic Invariants from Code Specifications for Agentic Property-Based Testing
AI Engineer,
Georgian Partners
Thursday, November 5th | 11:45 AM – 12:30 PM
A Code-First BI Architecture Powered by AI
Global Head of Data Platform and AI,
Rakuten Kobo
Toronto Summit · Presented by TMLS · Nov 5–6, 2026 · RBC WaterPark Place, TorontoThe people building agents, and the people building with them – one room, on the Toronto waterfront. Two days of practitioner-curated talks on what actually ships: the stack underneath agentic systems, and the products, workflows, and agents teams are running in production right now.