Anna Chernyshova
Sr Solutions Engineer @ Docker
Ottawa, Canada
Actions
Solutions Engineer focused on cloud-native architecture and developer experience. Passionate about developer productivity, fast feedback loops, and keeping the software supply chain secure as agent-driven workflows reshape how we build and ship software. Former Customer Success Engineer for Testcontainers Cloud and Quality Architect. Open-source contributor and conference speaker with a bias toward practical demos and real-world engineering problems.
Area of Expertise
Topics
MCP for Infrastructure with Containers, Docker Gateway, and Secure AI Agents
As LLMs become autonomous actors, MCP defines how they interact with tools, while containers define how they run safely.
In this workshop, using observability tools such as Grafana as an example, you'll learn how to run observability MCP servers as containers via Docker MCP Gateway and use them with sandboxed AI agents to manage dashboards and alerts using natural language, while preserving strong isolation and clear trust boundaries. We'll also show how this local setup maps cleanly to CI/CD pipelines, demonstrating how developers can start locally and scale the MCP-based architecture to Kubernetes.
By the end of the workshop, you'll have:
* A secure local MCP setup running in containers.
* AI agents in sandboxed environments interacting with real tools via Docker MCP Gateway.
* A path how to translate the local MCP experience to Kubernetes using Compose-For-Agents
Mastering Testcontainers: Build Custom Modules for Fun and Profit
Testcontainers has become the go-to solution for integration testing in the Java community. A key factor behind its popularity is its rich ecosystem of modules—predefined abstractions that allow you to spin up containerized services for your tests with just a single line of code.
But what if your projects frequently rely on a specific in-house technology and there is no Testcontainers module for it? Instead of repeatedly writing and copying integration code across different projects, you can build a custom Testcontainers module. It will help you to tailor Testcontainers to your needs, abstract away complexity, and ensure smooth integration with your internal Docker images.
In this lab, we’ll explore the architecture of a Testcontainers module, walk through the implementation process, and build couple of useful modules from scratch.
Whether you're working with databases, experimenting with chaos engineering, or looking to improve your team's testing workflow, creating a custom Testcontainers module is a powerful way to streamline integration testing and contribute to the Java ecosystem.
Testing AI Workflows Locally with Testcontainers
AI features now involve agents, tools, databases, and external systems working together. Most teams still test them manually or rely on mocks that do not reflect real behavior.
In this session, I will show how to test AI workflows using Testcontainers and real dependencies running locally.
We will build a setup where an AI agent interacts with tools and services, and run tests against it in a reproducible environment. You will see how to spin up dependencies on demand and validate real interactions instead of guessing.
This session is focused on making AI systems testable, reliable, and easier to develop.
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