Gemini Enterprise Agent Platform: Adding memory to AI agents

Опубликовано 19 мая 2026, 4:00

Google Cloud Data Agent Kit → goo.gle/4tBKZ8h
Google Developers Codelabs → goo.gle/43fQKhb
[GitHub] Race Condition → goo.gle/4dnsLBi

Join Google Cloud Developer Advocates Lucia Subin and Jack Weatherspoon as they recap their Dev Keynote demo, revealing how to build highly contextual AI agents using the Gemini Enterprise Agent Platform. Learn how to easily implement Agent Sessions and Memory Banks in under 20 lines of code to maintain statefulness, and discover how to leverage AlloyDB's auto embeddings and the new Data Agent Kit for seamless Retrieval-Augmented Generation (RAG). Empower your cloud workflows by exploring the open source "race condition" GitHub repository and utilizing pre-built Google Cloud Agent Skills to deploy scalable, intelligent data engineering pipelines today.

Chapters:
0:00 - Intro
0:55 - What are agent sessions & stateful agents?
1:39 - What is Memory Bank?
2:43 - What is Retrieval-Augmented Generation (RAG) & auto embedding in AlloyDB?
3:34 - What is the Google Cloud Data Agent Kit?
4:57 - Getting started today with codelabs
6:12 - Utilizing Google Cloud Agent Skills
7:29 - What is the Data Engineering Agent?
8:07 - Wrap up

More resources:
Google Agent Skills repo → goo.gle/4eUnyUi

Watch more Google Cloud Next 2026 → goo.gle/next-talks-2026
🔔 Subscribe to Google Cloud Tech → goo.gle/GoogleCloudTech

#GoogleCloudNext

Speakers: Lucia Subatin, Jack Wotherspoon
Products Mentioned: Gemini Enterprise Agent Platform, AlloyDB