From the course: Hands-On AI: Building Agents with the Google Agent Development Toolkit (ADK)

Unlock this course with a free trial

Join today to access over 25,000 courses taught by industry experts.

Conversational blueprint: Understanding session, state, and memory

Conversational blueprint: Understanding session, state, and memory

From the course: Hands-On AI: Building Agents with the Google Agent Development Toolkit (ADK)

Start my 1-month free trial Buy for my team

Conversational blueprint: Understanding session, state, and memory

“

- [Instructor] Have you ever wished your digital assistant could remember what you said earlier in the conversation or even what you discussed last week? In the world of multi-agent systems, context isn't just helpful, it's essential. Just like humans, agents need to recall what's been said and done to maintain continuity and avoid repetition. Let's learn how to give your agents real conversational memory using ADK's session, state, and memory features. We'll see how to manage context so your agents can hold multi-term conversations, remember user preferences, and even recall knowledge from past sessions. In ADK context is managed at three distinct levels, each serving a specific purpose. Session, or the current conversation thread, state, or the dynamic session scratch pad, and memory, or the cross session knowledge store. First up is the session. In ADK a session represents a single ongoing interaction between a user and your agent system. Think of it as one continuous conversation…

Contents