Your AI agent is forgetful. Here’s how to give it a brain.
Ai agent memory Google cloud ai Agent development kit Session state Multi Agent systems Ai agent persistence Serverless ai Google cloud platform Ai agent development Memory patterns for agents
This video covers three essential memory patterns for building AI agents that can remember conversations: session state, multi-agent state, and persistence. Part 1 of the Serverless Expeditions series, it uses Google's Agent Development Kit to demonstrate how to solve the 'Goldfish Problem' where agents forget context after a few minutes. Targeted at developers building production AI agents on Google Cloud who want their agents to maintain context across interactions.
Related videos
Build an AI agent app with Go ADK, Cloud Run, and Flutter
Building distributed multi-agent systems
From the I/O main stage to the terminal
The future of Cloud AI: Mastering MCP servers, Gemini, and agentic workflows
Building conversational applications with Bigtable and ADK
Your AI agent still has no memory? Fix it with these 3 patterns
Google’s Agents CLI is here: Build, eval, and deploy AI agents in minutes | The Agent Factory
What is Gemini Enterprise Agent Platform?
Gemma 4 production stack: Model Armor, ADK Agents, Tracing
I gave a Gemma 4 AI agent a sandbox and it taught itself physics | The Agent Factory Podcast
AlloyDB Lakehouse Federation: Unified access to BigQuery and Google Cloud Lakehouse
