{"course":{"productid":35885,"modality":1,"active":true,"language":"en","title":"Deploy Multi-Agent Systems with Agent Development Kit and Agent Engine","productcode":"DMASADKAE","vendorcode":"GO","vendorname":"Google","fullproductcode":"GO-DMASADKAE","courseware":{"has_ekit":false,"has_printkit":true,"language":""},"url":"https:\/\/portal.flane.ch\/course\/google-dmasadkae","objective":"<ul>\n<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>","essentials":"<p>Python, gen AI prompt engineering, gen AI tool use<\/p>","audience":"<p>Technical roles from partner organizations:\n<\/p>\n<ul>\n<li>Machine learning engineers<\/li><li>Gen AI engineers<\/li><\/ul>","outline":"<h4>Module 1 - Get started with the Agent Development Kit<\/h4><p>\n<strong>Topics<\/strong>\n<\/p>\n<ul>\n<li>Basics of building an agent in the Agent Development Kit.<\/li><\/ul><p>\n<strong>Objectives<\/strong>\n<\/p>\n<ul>\n<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><p><strong>Activities<\/strong>\n<\/p>\n<ul>\n<li>Lecture and lab demo<\/li><\/ul>\n<h4>Module 2 - Empower Agent Development Kit agents with tools\n<\/h4><p>\n<strong>Topics<\/strong>\n<\/p>\n<ul>\n<li>Enhance agents with tools and cover the growing breadth of available tools.<\/li><\/ul><p>\n<strong>Objectives<\/strong>\n<\/p>\n<ul>\n<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><p><strong>Activities<\/strong>\n<\/p>\n<ul>\n<li>Lab: Get started with Agent Development Kit (ADK)<\/li><li>Lab: Empower ADK agents with tools<\/li><\/ul>\n<h4>Module 3 - Build Multi-Agent Systems with Agent Development Kit\n<\/h4><p>\n<strong>Topics<\/strong>\n<\/p>\n<ul>\n<li>Manage communication and task-sharing between agents through parent-child relationships and flows to enable coordinated responses to queries.<\/li><\/ul><p><strong>Objectives<\/strong>\n<\/p>\n<ul>\n<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><p><strong>Activities<\/strong>\n<\/p>\n<ul>\n<li>Lab: Build multi-agent systems with ADK<\/li><\/ul><h4>Module 4 - Deploy Agent Development Kit agents to Agent Engine\n<\/h4><p>\n<strong>Topics<\/strong>\n<\/p>\n<ul>\n<li>Deploying agent apps to Agent Engine and querying responses.<\/li><\/ul><p>\n<strong>Objectives<\/strong>\n<\/p>\n<ul>\n<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><p>\n<strong>Activities<\/strong>\n<\/p>\n<ul>\n<li>Lab: Deploy ADK agents to Agent Engine<\/li><\/ul><h4>Module 5 - Evaluate agent systems<\/h4><p>\n<strong>Topics<\/strong>\n<\/p>\n<ul>\n<li>Evaluate agents within the Agent Development Kit.<\/li><\/ul><p>\n<strong>Objectives<\/strong>\n<\/p>\n<ul>\n<li>Evaluate agents within the Agent Development Kit.<\/li><li>Use the web interface to view evaluations.<\/li><\/ul>","summary":"<p>In this course, you&rsquo;ll learn to use the Google Agent Development Kit to build complex, Multi-Agent Systems. You will build agents equipped with tools, and connect them with parent-child relationships and flows to define how they interact. You&rsquo;ll run your agents locally and deploy them to Vertex AI Agent Engine to run as a managed agentic flow, with infrastructure decisions and resource scaling handled by Agent Engine.<\/p>","objective_plain":"- Build an agent with tools using the Google Agent Development Kit.\n- Establish interaction patterns between multiple agents with parent-child relationships and flows.\n- Utilize features such as session memory, artifact storage, and callbacks.\n- Deploy a multi-agent app to Agent Engine.\n- Query an agent app running on Agent Engine.","essentials_plain":"Python, gen AI prompt engineering, gen AI tool use","audience_plain":"Technical roles from partner organizations:\n\n\n\n- Machine learning engineers\n- Gen AI engineers","outline_plain":"Module 1 - Get started with the Agent Development Kit\n\n\nTopics\n\n\n\n- Basics of building an agent in the Agent Development Kit.\n\nObjectives\n\n\n\n- Explain how the Agent Development Kit compares to other tools such as the Google Gen AI SDK or LangChain.\n- Describe the parameters used to build an agent in Agent Development Kit.\nActivities\n\n\n\n- Lecture and lab demo\n\nModule 2 - Empower Agent Development Kit agents with tools\n\n\n\nTopics\n\n\n\n- Enhance agents with tools and cover the growing breadth of available tools.\n\nObjectives\n\n\n\n- Discuss the importance of structured docstrings and typing when writing tool functions for agents.\n- Demonstrate the ability to provide tools to an agent.\n- List common and useful tools available for the Agent Development Kit agents, including LangChain tools.\nActivities\n\n\n\n- Lab: Get started with Agent Development Kit (ADK)\n- Lab: Empower ADK agents with tools\n\nModule 3 - Build Multi-Agent Systems with Agent Development Kit\n\n\n\nTopics\n\n\n\n- Manage communication and task-sharing between agents through parent-child relationships and flows to enable coordinated responses to queries.\nObjectives\n\n\n\n- Describe the directory structure and naming conventions encouraged by the Agent Development Kit.\n- Demonstrate the ability to create multiple agents and relate them to one another with parent-child relationships.\n- Describe the different flow options and when you might use them.\n- Get responses that have passed through multiple agents.\n- Control content at different points with callbacks.\nActivities\n\n\n\n- Lab: Build multi-agent systems with ADK\nModule 4 - Deploy Agent Development Kit agents to Agent Engine\n\n\n\nTopics\n\n\n\n- Deploying agent apps to Agent Engine and querying responses.\n\nObjectives\n\n\n\n- Describe the benefits of deploying agents, especially Multi-Agent Systems, to Agent Engine over self-hosting, such as in Vertex AI online predictions.\n- Demonstrate deploying to Agent Engine.\n- Demonstrate querying a deployed agent app.\n\nActivities\n\n\n\n- Lab: Deploy ADK agents to Agent Engine\nModule 5 - Evaluate agent systems\n\n\nTopics\n\n\n\n- Evaluate agents within the Agent Development Kit.\n\nObjectives\n\n\n\n- Evaluate agents within the Agent Development Kit.\n- Use the web interface to view evaluations.","summary_plain":"In this course, you\u2019ll learn to use the Google Agent Development Kit to build complex, Multi-Agent Systems. You will build agents equipped with tools, and connect them with parent-child relationships and flows to define how they interact. You\u2019ll run your agents locally and deploy them to Vertex AI Agent Engine to run as a managed agentic flow, with infrastructure decisions and resource scaling handled by Agent Engine.","version":"1.0","duration":{"unit":"d","value":1,"formatted":"1 day"},"pricelist":{"List Price":{"US":{"country":"US","currency":"USD","taxrate":null,"price":595},"CA":{"country":"CA","currency":"CAD","taxrate":null,"price":820},"IT":{"country":"IT","currency":"EUR","taxrate":20,"price":650},"DE":{"country":"DE","currency":"EUR","taxrate":19,"price":950},"GB":{"country":"GB","currency":"GBP","taxrate":20,"price":660},"AT":{"country":"AT","currency":"EUR","taxrate":20,"price":950},"SE":{"country":"SE","currency":"EUR","taxrate":25,"price":950},"SI":{"country":"SI","currency":"EUR","taxrate":20,"price":950},"CH":{"country":"CH","currency":"CHF","taxrate":8.1,"price":950}}},"lastchanged":"2025-09-30T16:00:48+02:00","parenturl":"https:\/\/portal.flane.ch\/swisscom\/en\/json-courses","nexturl_course_schedule":"https:\/\/portal.flane.ch\/swisscom\/en\/json-course-schedule\/35885","source_lang":"en","source":"https:\/\/portal.flane.ch\/swisscom\/en\/json-course\/google-dmasadkae"}}