You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Which dates, particularly Tue/Wed/Thu during the 3rd/4th week of a month, are you likely available? (e.g. "Most Thursdays with 4 weeks notice", "June or later", etc.)
While AI agents may work well enough for local demos, moving to long-running agent workflows that interact with other services (internal microservices, GitHub, Slack, etc.) raises problems of scalability, security, durability, and resiliency. Triggering these workflows when certain business conditions are met is another problem — data is often spread across multiple data sources, which makes it difficult to express complex conditions.
In this talk, I'll give a brief overview of the change data processing capabilities of Drasi and the microservices APIs provided by Dapr, and how they can be combined to help application developers as well as platform/DevOps teams build and manage event-driven systems. I'll walk through a live demo showing how Dapr Agent workflows can be triggered from Drasi notifications in a Kubernetes environment, thanks to Dapr Agents' inherent support for asynchronous messaging and event-driven workflows. Lastly, I'll give a sneak peek at the upcoming work for the Google Summer of Code project as the focus shifts from purely reactive agents to autonomous, proactive agents.
Speaker Bio
Name: Jeffrey Zhang
Mini-bio: Jeffrey is a Computer Science student at the University of British Columbia. He is currently working on the CNCF Graduated project Dapr and the CNCF Sandbox project Drasi as part of Google Summer of Code 2026.
Picture for slides: (We use this pictures to create promotional content and to present your talk in our socials.)
While AI agents may work well enough for local demos, moving to long-running agent workflows that interact with other services (internal microservices, GitHub, Slack, etc.) raises problems of scalability, security, durability, and resiliency. Triggering these workflows when certain business conditions are met is another problem — data is often spread across multiple data sources, which makes it difficult to express complex conditions.
In this talk, I'll give a brief overview of the change data processing capabilities of Drasi and the microservices APIs provided by Dapr, and how they can be combined to help application developers as well as platform/DevOps teams build and manage event-driven systems. I'll walk through a live demo showing how Dapr Agent workflows can be triggered from Drasi notifications in a Kubernetes environment, thanks to Dapr Agents' inherent support for asynchronous messaging and event-driven workflows. Lastly, I'll give a sneak peek at the upcoming work for the Google Summer of Code project as the focus shifts from purely reactive agents to autonomous, proactive agents.
Speaker Bio