How Canva built an agentic support experience using Langfuse observability

Canva ML engineers Sergey Iakovlev and Sahil Bahl share how they took Canva's AI support systems from MVP to 250M+ users, covering agent tracing, prompt management, and continuous evaluation with Langfuse.

Canva's support experience is powered by multiple AI systems, from real-time assistance to asynchronous ticket resolution that handles complex, multi-step workflows and escalates to humans when needed.

In this session, Canva ML engineers Sergey Iakovlev and Sahil Bahl share how they took these systems from MVP to serving Canva’s 250M+ users, and the infrastructure built along the way to get there safely.

They cover how traces helped debug complex agent workflows, how prompt management unlocked safe iteration through shadowing and localisation, and how they built continuous evaluation loops using LLM-as-judge, offline datasets, and human feedback, using tools like Langfuse alongside internal tooling we developed.

Hear practical lessons from running experiments, replaying real support scenarios, and the things they wish they'd known earlier about scaling AI systems in production.

This is an Open House Roadshow Australia 2026 session.