Diana Zawadzki
Software Engineer, Uber
San Francisco, California, United States
Actions
Diana Zawadzki is a Software Engineer at Uber and a maintainer of Cadence Workflow, an open-source CNCF project, where she works on durable orchestration for AI agents, keeping long-running workflows reliable through crashes, retries, and approval steps. She previously worked on Michelangelo, Uber’s AI/ML platform, and studied Computer Science at Stanford with a focus on distributed systems.
Area of Expertise
Secure Your Agents in 5 Minutes: Durable Execution with Cadence
Agents fail in boring ways. A tool times out, a model call errors, a worker restarts, or a human approval takes six hours, and the agent loses its place.
Cadence is a CNCF sandbox project for durable workflow orchestration, and the engine Uber runs its production agentic workflows on. In five minutes, I will show what changes when an agent runs as a Cadence workflow: state is persisted, failed steps retry, approvals can wait as long as they need, and every decision lands in a history you can inspect.
You will leave with a simple test for when an agent should become a durable workflow, a clear picture of where Cadence sits in the AI stack, and a way in: docs, samples, and an invitation to our ContribFest.
Cadence Workflow ContribFest: Build Durable AI Agent Examples
Cadence already runs agentic workflows in production at Uber. This session is about making that path easy for everyone else. Join the Cadence maintainers, pick an issue at your level, and start shipping.
Beginners run the local agent example and fix whatever slowed them down. Intermediate contributors build agent tools with retries and fault tolerance. Advanced contributors take on stateful, multi-step agent samples. Maintainers are in the room the whole time to answer questions and review PRs.
Everything runs locally against an open-weight model, so you do not need an API key. Bring a laptop, and install Ollama beforehand if you can. No Cadence experience needed.
Agents Fail. Workflows Recover. Durable Agent Orchestration with Cadence.
Uber's AI/ML platform, Michelangelo, runs its agents on Cadence. Its Agent Executor Service uses Cadence as the durability layer for agentic workflows in production, serving teams across the company. An agent that crashes, stalls, or waits days on a human picks up exactly where it left off.
This session explains why that layer is needed and how to build it. Most agent SDKs are stateless by design, which makes them fragile where production is hardest: process crashes, hanging tools, and tasks that run for days. With Cadence underneath, a run resumes instead of restarting, every decision and tool call is recorded and replayable, and a long wait costs nothing.
We cover the architecture behind Uber's setup and what it takes to keep agents reliable at that scale. We then walk through the Cadence integrations for agent SDKs such as OpenAI Agents and Google ADK, and the AI coding tool skills that get you to a first durable agent workflow in minutes.
You will leave with a blueprint for making your agents as reliable as your microservices.
Project Lightning Talk + ContribFest + Maintainer Track: KubeCon + CloudNativeCon NA 2026 Sessionize Event Upcoming
KubeCon + CloudNativeCon North America 2026 Sessionize Event Upcoming
Diana Zawadzki
Software Engineer, Uber
San Francisco, California, United States
Actions
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top