Join GDG London for a deep dive into the frontiers of Google's AI ecosystem, exploring how advanced models are being used to build our digital world and understand our physical planet.
In the first half of our evening, we will dive into the developer's command line with Max Shaposhnikov (Research Engineer, Tessl) for a practical tour of the Gemini CLI, Google's powerful open-source coding agent. This session goes beyond basic prompting to explore the core principles and design choices that govern agent behaviour. Max will dissect its standout features, including long-term memory with a massive 1M-token context window, checkpoints, sandboxing environments, and extensions. Through live demos, we’ll investigate its real-world coding skills and answer practical questions: Can Gemini handle complex backend development? What about UI work? You'll walk away from this session with actionable tips and a deeper understanding of how to leverage sophisticated AI agents in your own projects.
From the intricacies of AI-native engineering, we'll then zoom out to a planetary perspective with Pier Paolo Ippolito (GenAI Solutions Architect) and Michelangelo Conserva (Research Scientist, Google). They will introduce the Google Earth Engine and the groundbreaking AlphaEarth Foundations model from Google DeepMind. Discover how this technology unifies vast and diverse Earth observation data - from satellite and radar imagery to climate simulations-into a single, powerful "embedding." Learn how this approach dramatically enhances efficiency, requiring 16 times less storage space while mapping the globe in sharp 10x10 meter squares. This session will reveal how scientists can now create highly accurate, on-demand maps to monitor critical global issues like deforestation, urban expansion, and water resources with unprecedented clarity.
Location: Tessl HQ, 4th Floor, 210 Pentonville Rd, London N1 9JY
Agenda
5:30 PM: Doors Open, Networking & Refreshments
6:00 PM: Welcome & Community Updates
6:10 PM: Inside Gemini CLI: An Open-Source Agent Toolkit (45 mins)
A practical tour of Gemini CLI, Google’s open-source toolkit for coding agents.
Max will unpack its core design principles, from built-in tools and system prompts to memory, context management, and sandboxed environments, and show how developers can tailor and extend it for their own workflows.
Highlights:
How Gemini CLI’s architecture enables agent reasoning and tool use
Demonstration of long-term memory (1 M-token context), checkpoints, and reusable prompts
Sandbox environments for safe code execution
Practical examples of backend and UI development with Gemini
Live demo snippets and take-home tips for AI-native engineering
6:55 PM: Break (15 mins)
7:10 PM: Talk 2: Mapping the Future with Google Earth Engine & AlphaEarth (45 mins)
The talks introduce GEE with a focus on the latest remote sensing foundational model from GDM, AlphaEarth Foundations
Unified Data Representation: They integrate vast and diverse Earth observation data-including optical satellite images, radar, 3D laser mapping, and climate simulations-into a single, unified "embedding" that computers can easily process.
High Efficiency and Detail: The embeddings are highly compact, requiring 16 times less storage space than other tested AI systems, which dramatically reduces the cost of planetary-scale analysis while still characterizing the Earth in sharp 10x10 meter squares.
Accurate, On-Demand Mapping: This technology enables scientists to create detailed and consistent maps on-demand with high accuracy (showing a 24% lower error rate than other models), even in areas with sparse data, to better monitor critical issues like deforestation, urban expansion, and water resources.
7:55 PM: Further Networking
8:30 PM: Event Close
---
Speakers
Pier Paolo Ippolito - Google
GenAI Solutions Architect at Google and INSEAD Alumni with an interest in research areas such as Data Science, Machine Learning and Product Development. As a result of my work experience, I had the opportunity to work with large scale software projects collaborating effectively within different teams. Aside from my work activities, I am a technical writer/editor (more than 1.5M views) and Azur…
Michelangelo Conserva - Google (Research Scientist)
Michelangelo is a Research Scientist at Google whose work focuses on the latest remote sensing foundational models, including AlphaEarth Foundations from Google DeepMind.
Max Shaposhnikov - Tessl (Research Engineer)
Max is an AI Research Engineer at Tessl, where he is pioneering AI code generation through a Spec-Driven Development approach. He previously worked as an Applied Scientist at Amazon, focusing on pre-training multimodal LLMs for products such as the Alexa voice assistant. Beyond hands-on research and engineering, Maxim enjoys teaching machine learning, breaking down complex concepts into simple…
Hosted By
Renuka Kelkar, GDG Organizer
Sumith Damodaran, PM / GDG Organizer
Chris Bouloumpasis, GDG Organizer
Goran Minov, Regional Technical Strategist | GDG Organizer
Inès Rigaud, GDG Organizer
Mihaela Peneva, GDG Organizer
Stefan Cornea, GDG Organizer
Sara Mita Gabriel, Organiser
Complete your event RSVP here: https://gdg.community.dev/events/details/google-gdg-london-presents-the-ai-spectrum-from-earths-surface-to-the-developers-cli/.
