Date: September 24, 2026
Time: 11:00 am – 12:00 pm SGT
Not long ago, the users of an AI application were people. They browsed, paused, and thought between clicks, and every backend built for that traffic inherited its rhythm. Agent traffic has none of it. Agents fan out, retry, and hold state across many steps, bursting without warning and scaling with the value of the work rather than the number of people doing it.
The platforms sitting closest to that shift see it first. Dify sits between builders and the models they ship against, with more than a million applications deployed on the platform. This makes it an early read on how agent workloads behave in production rather than how anyone expected them to. Some of what the team is seeing was not on the roadmap a year ago, and it tends to surface as an infrastructure problem before anyone names it as one.
In this 30-minute fireside chat, Lusha Chen, General Manager of APAC at Dify, and Terry Purcell, TiDB’s Field CTO and Principal Architect, take the move from apps to agents from both ends: what agents are doing that human users never did, and which assumptions in the data layer break first when the user is a machine. This will be a moderated conversation, no slides, with live audience Q&A at the end.
What you’ll learn:
- How agent workloads differ from human traffic, and why the difference shows up as an infrastructure problem before anyone names it as one.
- What the Dify team is seeing as builders move from apps to agents, including the patterns that caught them off guard.
- Which data-layer assumptions break first when the user is an agent rather than a person.
- What an agent-native data layer has to handle differently for memory, state, and bursty concurrency.
- What builders are asking for now that they were not asking for a year ago.
- Where this goes over the next twelve months, and the one thing to do this quarter if agents are coming for your stack.
This session is built for builders, engineering leaders, and platform teams thinking through the move from apps to agents. If you are deciding what your infrastructure needs to handle next, you won’t want to miss this discussion.
Speakers:
Lusha Chen, General Manager (APAC), Dify
Lusha leads Dify across the region, working directly with the teams building AI applications in APAC markets. Her work puts her close to how agent workloads behave in the wild — what is changing in how AI applications get built, which patterns are emerging as builders move from apps to agents, and what those teams are asking their infrastructure to do next.
Terry Purcell, Field CTO and Principal Architect, TiDB
Terry brings decades of enterprise database experience to the role, spanning query optimization, distributed systems performance, and large-scale enterprise database architecture, along with more than 40 US patents. At TiDB, he advises organizations on the data infrastructure decisions behind production AI workloads, helping technical leaders evaluate where traditional systems break down under agentic AI traffic and what architectural patterns hold up at scale.