How Canva built an Agentic Support Experience using Langfuse Observability
At Canva, our 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 talk, we’ll share how we took these systems from MVP to serving Canva’s 250M+ users, and the infrastructure we built along the way to get there safely.
We’ll cover how traces helped us debug complex agent workflows, how prompt management unlocked safe iteration through shadowing and localisation, and how we built continuous evaluation loops using LLM-as-judge, offline datasets, and human feedback, using tools like Langfuse alongside internal tooling we developed.
We’ll also share practical lessons from running experiments, replaying real support scenarios, and the things we wish we’d known earlier about scaling AI systems in production.
Sergey Lakovlev
Sergey Lakovlev is a Lead ML Engineer at Canva, where he builds the AI-powered customer support experience that serves millions of users. His work spans the full stack of production LLM systems: retrieval architectures, QA chatbots, agentic systems for automated ticket resolution, and the evaluation and traceability infrastructure that makes deploying them safe at scale. Before Canva, Sergey worked on automated driving at Bosch and at several startups in Melbourne and Russia.
Sahil Bahl
Sahil Bahl is a Senior Machine Learning Engineer at Canva, where he focuses on scaling customer support using AI. His work involves building production-grade agentic systems for automated ticket resolution, content validation, and customer service copilots, with a strong emphasis on observability, evaluation, and reliability in real-world deployments. Previously, Sahil led the design and delivery of enterprise AI solutions at Mantel Group, establishing MLOps frameworks and deploying scalable systems across cloud platforms. His experience spans retrieval-augmented generation, multimodal LLMs, and production monitoring. He is a regular speaker at AI community events, including AWS Community Day and meetups across Australia and New Zealand.