Deploy Multi-Agent Systems with Agent Development Kit and Agent Engine

Deploy Multi-Agent Systems with Agent Development Kit and Agent EngineDMASADKAEGOGoogleGO-DMASADKAE1.0<ul> <li>Build an agent with tools using the Google Agent Development Kit.</li><li>Establish interaction patterns between multiple agents with parent-child relationships and flows.</li><li>Utilize features such as session memory, artifact storage, and callbacks.</li><li>Deploy a multi-agent app to Agent Engine.</li><li>Query an agent app running on Agent Engine.</li></ul>Python, gen AI prompt engineering, gen AI tool useTechnical roles from partner organizations: <ul> <li>Machine learning engineers</li><li>Gen AI engineers</li></ul><h4>Module 1 - Get started with the Agent Development Kit</h4> Topics <ul> <li>Basics of building an agent in the Agent Development Kit.</li></ul> Objectives <ul> <li>Explain how the Agent Development Kit compares to other tools such as the Google Gen AI SDK or LangChain.</li><li>Describe the parameters used to build an agent in Agent Development Kit.</li></ul>Activities <ul> <li>Lecture and lab demo</li></ul> <h4>Module 2 - Empower Agent Development Kit agents with tools </h4> Topics <ul> <li>Enhance agents with tools and cover the growing breadth of available tools.</li></ul> Objectives <ul> <li>Discuss the importance of structured docstrings and typing when writing tool functions for agents.</li><li>Demonstrate the ability to provide tools to an agent.</li><li>List common and useful tools available for the Agent Development Kit agents, including LangChain tools.</li></ul>Activities <ul> <li>Lab: Get started with Agent Development Kit (ADK)</li><li>Lab: Empower ADK agents with tools</li></ul> <h4>Module 3 - Build Multi-Agent Systems with Agent Development Kit </h4> Topics <ul> <li>Manage communication and task-sharing between agents through parent-child relationships and flows to enable coordinated responses to queries.</li></ul>Objectives <ul> <li>Describe the directory structure and naming conventions encouraged by the Agent Development Kit.</li><li>Demonstrate the ability to create multiple agents and relate them to one another with parent-child relationships.</li><li>Describe the different flow options and when you might use them.</li><li>Get responses that have passed through multiple agents.</li><li>Control content at different points with callbacks.</li></ul>Activities <ul> <li>Lab: Build multi-agent systems with ADK</li></ul><h4>Module 4 - Deploy Agent Development Kit agents to Agent Engine </h4> Topics <ul> <li>Deploying agent apps to Agent Engine and querying responses.</li></ul> Objectives <ul> <li>Describe the benefits of deploying agents, especially Multi-Agent Systems, to Agent Engine over self-hosting, such as in Vertex AI online predictions.</li><li>Demonstrate deploying to Agent Engine.</li><li>Demonstrate querying a deployed agent app.</li></ul> Activities <ul> <li>Lab: Deploy ADK agents to Agent Engine</li></ul><h4>Module 5 - Evaluate agent systems</h4> Topics <ul> <li>Evaluate agents within the Agent Development Kit.</li></ul> Objectives <ul> <li>Evaluate agents within the Agent Development Kit.</li><li>Use the web interface to view evaluations.</li></ul>- Build an agent with tools using the Google Agent Development Kit. - Establish interaction patterns between multiple agents with parent-child relationships and flows. - Utilize features such as session memory, artifact storage, and callbacks. - Deploy a multi-agent app to Agent Engine. - Query an agent app running on Agent Engine.Python, gen AI prompt engineering, gen AI tool useTechnical roles from partner organizations: - Machine learning engineers - Gen AI engineersModule 1 - Get started with the Agent Development Kit Topics - Basics of building an agent in the Agent Development Kit. Objectives - Explain how the Agent Development Kit compares to other tools such as the Google Gen AI SDK or LangChain. - Describe the parameters used to build an agent in Agent Development Kit. Activities - Lecture and lab demo Module 2 - Empower Agent Development Kit agents with tools Topics - Enhance agents with tools and cover the growing breadth of available tools. Objectives - Discuss the importance of structured docstrings and typing when writing tool functions for agents. - Demonstrate the ability to provide tools to an agent. - List common and useful tools available for the Agent Development Kit agents, including LangChain tools. Activities - Lab: Get started with Agent Development Kit (ADK) - Lab: Empower ADK agents with tools Module 3 - Build Multi-Agent Systems with Agent Development Kit Topics - Manage communication and task-sharing between agents through parent-child relationships and flows to enable coordinated responses to queries. Objectives - Describe the directory structure and naming conventions encouraged by the Agent Development Kit. - Demonstrate the ability to create multiple agents and relate them to one another with parent-child relationships. - Describe the different flow options and when you might use them. - Get responses that have passed through multiple agents. - Control content at different points with callbacks. Activities - Lab: Build multi-agent systems with ADK Module 4 - Deploy Agent Development Kit agents to Agent Engine Topics - Deploying agent apps to Agent Engine and querying responses. Objectives - Describe the benefits of deploying agents, especially Multi-Agent Systems, to Agent Engine over self-hosting, such as in Vertex AI online predictions. - Demonstrate deploying to Agent Engine. - Demonstrate querying a deployed agent app. Activities - Lab: Deploy ADK agents to Agent Engine Module 5 - Evaluate agent systems Topics - Evaluate agents within the Agent Development Kit. Objectives - Evaluate agents within the Agent Development Kit. - Use the web interface to view evaluations.1 day595.00820.00650.00950.00660.00950.00950.00950.00950.00