[{"@context":"https:\/\/schema.org\/","@type":"BlogPosting","@id":"https:\/\/blog.terabox.com\/insights\/master-gemini-api-stateful-ai-agents#BlogPosting","mainEntityOfPage":"https:\/\/blog.terabox.com\/insights\/master-gemini-api-stateful-ai-agents","headline":"Master Gemini API: Build Stateful AI Agents with DeepMind","name":"Master Gemini API: Build Stateful AI Agents with DeepMind","description":"\ud83d\udcfa Today’s recommended deep-dive video: https:\/\/www.youtube.com\/watch?v=cVzf49yg0D8 Building the Future of AI Agents: Mastering Gemini\u2019s Interactions and Live APIsThe Evolution of the Interactions APIHands-On: Building a Coding AgentNative Multimodal: The Gemini Live APIScaling and Production ChallengesKey TakeawaysQ&A Building the Future of... ","datePublished":"2026-07-22","dateModified":"2026-07-22","author":{"@type":"Person","@id":"https:\/\/blog.terabox.com\/author\/flextech-admin\/#Person","name":"flextech-admin","url":"https:\/\/blog.terabox.com\/author\/flextech-admin\/","image":{"@type":"ImageObject","@id":"https:\/\/secure.gravatar.com\/avatar\/ad516503a11cd5ca435acc9bb6523536?s=150&d=mm&r=gforcedefault=1","url":"https:\/\/secure.gravatar.com\/avatar\/ad516503a11cd5ca435acc9bb6523536?s=150&d=mm&r=gforcedefault=1","height":96,"width":96}},"publisher":{"@type":"Organization","name":"terabox","logo":{"@type":"ImageObject","@id":"http:\/\/blog.terabox.com\/wp-content\/uploads\/2021\/11\/logo\u4ea7\u54c1\u540d-\u7ad6\u7248.png","url":"http:\/\/blog.terabox.com\/wp-content\/uploads\/2021\/11\/logo\u4ea7\u54c1\u540d-\u7ad6\u7248.png","width":900,"height":900}},"image":{"@type":"ImageObject","@id":"https:\/\/img.youtube.com\/vi\/cVzf49yg0D8\/maxresdefault.jpg","url":"https:\/\/img.youtube.com\/vi\/cVzf49yg0D8\/maxresdefault.jpg","height":"","width":""},"url":"https:\/\/blog.terabox.com\/insights\/master-gemini-api-stateful-ai-agents","video":{"@context":"http:\/\/schema.org\/","@type":"VideoObject","@id":"https:\/\/www.youtube.com\/watch?v=cVzf49yg0D8#VideoObject","contentUrl":"https:\/\/www.youtube.com\/watch?v=cVzf49yg0D8","name":"Building Conversational Agents \u2014 Thor Schaeff and Philipp Schmid, Google DeepMind","description":"Thor Schaeff and Philipp Schmid show how to build conversational agents with Google DeepMind's Gemini APIs, from tool-using coding agents to realtime voice interfaces. The session covers the new Interactions API, agent skills, server-side state, and the Live API workflow for streaming audio, video, and tool calls into multimodal assistants.\n\nSpeaker info:\n- https:\/\/x.com\/_philschmid\n- https:\/\/x.com\/thorwebdev\n\nTimestamps\n0:14 - Introduction and speaker introductions\n6:15 - Audience interaction and project discussions\n8:38 - Introduction to building conversational agents\n28:17 - Discussion on Gemini Flash for coding and agentic use\n36:28 - Coding agent implementation and tool calling demonstration\n42:55 - Overview of the Interactions API and state management\n49:05 - Introduction to the Gemini Live API\n50:02 - Live Jukebox demo with music generation\n54:49 - Deep dive into Gemini Flash Live features (multimodality, latency, tools)\n1:06:54 - Technical setup and implementation of the Live API using WebSockets\n1:25:14 - Session management and context window compression\n1:26:57 - Real-world business use cases for conversational agents\n1:35:02 - Multimodal grounding and handling audio inputs\n1:40:00 - Discussion on personalization and speaker identification","thumbnailUrl":["https:\/\/i.ytimg.com\/vi\/cVzf49yg0D8\/default.jpg","https:\/\/i.ytimg.com\/vi\/cVzf49yg0D8\/mqdefault.jpg","https:\/\/i.ytimg.com\/vi\/cVzf49yg0D8\/hqdefault.jpg","https:\/\/i.ytimg.com\/vi\/cVzf49yg0D8\/sddefault.jpg","https:\/\/i.ytimg.com\/vi\/cVzf49yg0D8\/maxresdefault.jpg"],"uploadDate":"2026-04-30T16:00:06+00:00","duration":"PT1H47M34S","embedUrl":"https:\/\/www.youtube.com\/embed\/cVzf49yg0D8","publisher":{"@type":"Organization","@id":"https:\/\/www.youtube.com\/channel\/UCLKPca3kwwd-B59HNr-_lvA#Organization","url":"https:\/\/www.youtube.com\/channel\/UCLKPca3kwwd-B59HNr-_lvA","name":"AI Engineer","description":"We turn high signal in-person events for the top AI engineers, founders, leaders, and researchers in the world into the best free learning opportunities for millions around the world here on YouTube. Your subscribes, likes, comments, speaking, attendance, or sponsorships goes a long way toward making our biz model sustainable indefinitely.\n\nWe strongly believe this industry deserves a better class of community and that we know how to do this well; we just need your support.\n","logo":{"url":"https:\/\/yt3.ggpht.com\/ajVemEB89DAOemsbfuMY6ZOWXJAACx3cbty9z21jeqRKODaVkDBSRun1b1xfQJljEsziOWS_Mg=s800-c-k-c0x00ffffff-no-rj","width":800,"height":800,"@type":"ImageObject","@id":"https:\/\/www.youtube.com\/watch?v=cVzf49yg0D8#VideoObject_publisher_logo_ImageObject"}},"potentialAction":{"@type":"SeekToAction","@id":"https:\/\/www.youtube.com\/watch?v=cVzf49yg0D8#VideoObject_potentialAction","target":"https:\/\/www.youtube.com\/watch?v=cVzf49yg0D8&t={seek_to_second_number}","startOffset-input":"required name=seek_to_second_number"},"interactionStatistic":[[{"@type":"InteractionCounter","@id":"https:\/\/www.youtube.com\/watch?v=cVzf49yg0D8#VideoObject_interactionStatistic_WatchAction","interactionType":{"@type":"WatchAction"},"userInteractionCount":6272}],{"@type":"InteractionCounter","@id":"https:\/\/www.youtube.com\/watch?v=cVzf49yg0D8#VideoObject_interactionStatistic_LikeAction","interactionType":{"@type":"LikeAction"},"userInteractionCount":137}]},"about":["Insights","\u300eEnglish\u300f"],"wordCount":1484,"keywords":["permanent","sync"]},{"@context":"https:\/\/schema.org\/","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Insights","item":"https:\/\/blog.terabox.com\/insights\/#breadcrumbitem"},{"@type":"ListItem","position":2,"name":"Master Gemini API: Build Stateful AI Agents with DeepMind","item":"https:\/\/blog.terabox.com\/insights\/master-gemini-api-stateful-ai-agents#breadcrumbitem"}]}]