Software Engineer and Developer Advocate at Google
London, United Kingdom
I’m a Software Engineer and a Developer Advocate at Google in London. I build tools, demos, tutorials, and give talks to educate and help developers to be successful on Google Cloud.
Agent Protocols: MCP, A2A, and ADK in Action
Model Context Protocol (MCP) standardizes how models and agents access external tools and resources. Agent2Agent (A2A) Protocol defines how agents running on diverse frameworks and platforms communicate. Together, MCP and A2A enable collaborative agent ecosystems with seamless interoperability.
In this session, we’ll unpack both protocols, show how they complement each other. We’ll then see demos on how to implement these protocols in agent frameworks such as Agent Development Kit (ADK) and deploy them to the cloud to give you practical knowledge to start building your own interoperable agents.
Coding in the Agentic Era
AI tools has fundamentally changed the way we code. The landscape is a diverse and often confusing maze of tools–from smart autocompletion and web-based vibe coding to CLI/GitHub agents and fully agentic IDEs.
In this demo-driven session, we’ll explore the AI tools landscape, providing a clear overview and essential best practices to help you get the most out of these tools.
Beyond the Prompt: Evaluating, Testing, and Securing LLM Applications
When you change prompts or modify the Retrieval-Augmented Generation (RAG) pipeline in your LLM applications, how do you know it’s making a difference? You don’t—until you measure. But what should you measure, and how? Similarly, how can you ensure your LLM app is resilient against prompt injections or avoids providing harmful responses? More robust guardrails on inputs and outputs are needed beyond basic safety settings.
In this talk, we’ll explore various evaluation frameworks such as Vertex AI Evaluation, DeepEval, and Promptfoo to assess LLM outputs, understand the types of metrics they offer, and how these metrics are useful. We’ll also dive into testing and security frameworks like LLM Guard to ensure your LLM apps are safe and limited to precisely what you need.
Avoid common LLM pitfalls
It’s easy to generate content with a Large Language Model (LLM), but the output often suffers from hallucinations (fake content), outdated information (not based on the latest data), reliance on public data only (no private data), and a lack of citations back to original sources. Not ideal for real-world applications. In this talk, we’ll provide a quick overview of the latest advancements in multi-modal LLMs, highlighting their capabilities and limitations. We’ll then explore various techniques to overcome common LLM pitfalls, including Retrieval-Augmented Generation (RAG) to enhance prompts with relevant data, ReACT prompting to guide LLMs in verbalizing their reasoning, Function Calling to grant LLMs access to external APIs, and Grounding to link LLM outputs to verifiable information sources, and more.
Building your AI agent with Agent Development Kit (ADK)
Join this workshop to get hands-on experience with the Agent Development Kit (ADK), the Google’s open-source framework for building flexible and powerful AI agents. You’ll have the opportunity to learn how ADK’s building blocks accelerate the development, testing, and evaluation of your agents. Through guided exercises, you will build a functional multi-agent application, test it locally, and deploy it to Google Cloud with the tools provided by ADK.
Building with Antigravity: Google’s agentic development platform
Antigravity (AGY) is Google’s agentic development platform designed to let you build with agents at whatever abstraction level you prefer. With an intuitive, artifact-based approach to feedback, AGY meets you where you are across four main interfaces:
- AGY: A no-code environment to spin up and orchestrate multiple parallel agents across workspaces.
- AGY IDE: Transforms your regular IDE into an agentic workspace, bringing you closer to the code.
- AGY CLI: Brings agentic orchestration directly to your terminal.
- AGY SDK: The core AGY harness that lets you embed advanced agent capabilities and custom workflows directly into your own applications.
In this demo-driven deep dive, you’ll get a comprehensive tour of the AGY landscape and learn how to utilize dynamic parallel agents using skills, MCP servers, lifecycle hooks, rules, workflows, sidecars, and more.
Gemini for developers
Gemini is Google’s family of multimodal AI models. In this talk, you’ll learn about the models, witness their powerful capabilities such as deep thinking, Google Search and Map grounding, computer use tool, spatial understanding, live API, and native image and audio output. You’ll also see demos of Gemini’s coding agent tools Antigravity and Gemini CLI, and also learn how to integrate Gemini into your applications using the Google Gen AI SDK.
SDD 2025 Sessionize Event
May 2025 London, United Kingdom
DevFest London 2024 Sessionize Event
November 2024 London, United Kingdom
Jfokus 2024 Sessionize Event
February 2024 Stockholm, Sweden
FooConf #2 Sessionize Event
November 2023 Helsinki, Finland
CloudWorld 2022 Sessionize Event
February 2022 Oakland, California, United States
J-Fall 2021 Sessionize Event
November 2021 Ede, The Netherlands
GDG DevFest UK & Ireland 2020 Sessionize Event
October 2020 London, United Kingdom
ITCamp 2019 Sessionize Event
June 2019 Cluj-Napoca, Romania
Mete Atamel
Software Engineer and Developer Advocate at Google
London, United Kingdom