Gemini Enterprise Agent Platform: Adding memory to AI agents

Google Cloud Tech · Beginner ·🔍 RAG & Vector Search ·1mo ago

Skills: Agent Foundations80%

Key Takeaways

Building highly contextual AI agents using the Gemini Enterprise Agent Platform

Original Description

Google Cloud Data Agent Kit → https://goo.gle/4tBKZ8h Google Developers Codelabs → https://goo.gle/43fQKhb [GitHub] Race Condition → https://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 → https://goo.gle/4eUnyUi Watch more Google Cloud Next 2026 → https://goo.gle/next-talks-2026 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech #GoogleCloudNext Speakers: Lucia Subatin, Jack Wotherspoon Products Mentioned: Gemini Enterprise Agent Platform, AlloyDB

Watch on YouTube ↗ (saves to browser)

Sign in to unlock AI tutor explanation · ⚡30

More on: Agent Foundations

View skill →

Build and Deploy an Agent with Reasoning Engine in Vertex AI

Adding a Phone Gateway to a Virtual Agent

From Zero to Working AI Agent in 60 Seconds

From Zero to Working AI Agent in 60 Seconds

Create An AI Agent With Replit That Automates Your Sales

Create An AI Agent With Replit That Automates Your Sales

Capstone: Autonomous Runway Detection for IoT

Capstone: Autonomous Runway Detection for IoT

AI Agents with Model Context Protocol & Typescript

AI Agents with Model Context Protocol & Typescript

Related Reads

Production RAG for enterprises: evaluation, safety, and cost

Learn how to evaluate and implement production-ready RAG for enterprises, focusing on safety and cost efficiency

RAG for Financial Docs Is Different. Here’s the Chunking Strategy That Finally Worked.

Learn how to apply a structure-aware chunking strategy to improve RAG for financial documents, overcoming the limitations of generic 512-token chunks

RAG: Every Data Type You'll Actually Run Into (Part 2)

Learn to handle real-world data for RAG by understanding common data types and preparing them for vector stores

RAG: Every Data Type You'll Actually Run Into (Part 2)

Learn to handle real-world data for RAG by preparing it for vector stores, a crucial step in implementing RAG effectively

Chapters (9)

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

OpenAI Embeddings and Vector Databases Crash Course