--- schema: 1 type: video title: 'An Interaction Is All You Need — Ivan Leo, Google DeepMind' description: >- Models became agents, and the APIs didn't keep up. Google DeepMind rebuilt them. Ivan Leo, developer experience engineer at Google DeepMind, introduces the Gemini Interactions API and Managed Agents. He traces how we went from single completions to function calling to agents, then shows server-side state with interaction IDs (no more hand-managing thought signatures), strongly typed multimodal outputs, mixing built-in and custom tools, and the new steps data model. He then demos Managed Agents, which run the Antigravity harness in a persistent remote sandbox with environment IDs, loadable sources, a credential-injecting proxy and named agents, plus the open-source Gemini API CLI. In this talk: • Why agent workloads need a different API shape • Server-side state: interaction IDs and thought signatures • Chaining image, video and audio generation with the same context • Managed Agents: persistent sandboxes, skills, secure credentials and named agents SPEAKER Ivan Leo, Developer Experience Engineer, Google DeepMind LinkedIn: https://www.linkedin.com/in/ivanleo X: https://x.com/ivanleomk GitHub: https://github.com/ivanleomk Website: https://ivanleo.com/ LINKS Interactions API overview: https://ai.google.dev/gemini-api/docs/interactions-overview Managed Agents quickstart: https://ai.google.dev/gemini-api/docs/managed-agents-quickstart Antigravity agent: https://ai.google.dev/gemini-api/docs/antigravity-agent Gemini API CLI (GitHub): https://github.com/google-gemini/gemini-api-cli Google AI Studio: https://ai.google.dev/aistudio CHAPTERS 0:00 Intro 0:12 Interactions API and Managed Agents 0:27 From single completions to agents 1:02 Function calling 1:32 Models that reason and act 2:02 What is an agent? 3:02 Try the models in AI Studio 4:07 Why a new API 5:31 Server-side state and thought signatures 6:21 Demo: chaining image and video generation 7:01 How the code works 7:36 Strongly typed outputs 8:21 Mixing built-in and custom tools 9:01 The steps data model 9:46 Managed Agents: Antigravity in the cloud 10:36 Demo: analyzing a GitHub repo 11:06 Persistent sandboxes with environment IDs 11:41 Loading sources: GCS, GitHub, inline files 12:16 A 2M-token repo analysis 12:56 The same agent locally and in the cloud 13:36 A credential-injecting proxy 14:26 Named agents 15:26 The Gemini API CLI 15:56 Migrating with the Interactions API skill 16:36 Wrap-up Recorded at the AI Engineer World's Fair 2026 in San Francisco. Subscribe for more talks from the engineers building with AI. AI Engineer: https://ai.engineer YouTube: https://www.youtube.com/@aiDotEngineer X: https://x.com/aiDotEngineer LinkedIn: https://www.linkedin.com/company/aidotengineer/ #Gemini #AIAgents #AIEngineer canonical: >- https://liquidgold.cc/channel/aidotengineer/explore/video/an-interaction-is-all-you-need-ivan-leo-google-deep-07e67a47b3fd markdown: >- https://liquidgold.cc/channel/aidotengineer/video/an-interaction-is-all-you-need-ivan-leo-google-deep-07e67a47b3fd.md llms: null parent: 'https://liquidgold.cc/channel/aidotengineer.md' channel: aidotengineer updated: '2026-10-23T22:20:05.014Z' language: null children: [] videoId: 8aVbXXvJUY4 durationSeconds: 1024 publishedAt: '2026-10-03T19:30:16.000Z' searchChunks: - ordinal: 0 text: null startSeconds: 12 endSeconds: 33 watch: 'https://liquidgold.cc/watch/8aVbXXvJUY4?t=12' heldReason: rights - ordinal: 1 text: null startSeconds: 44 endSeconds: 66 watch: 'https://liquidgold.cc/watch/8aVbXXvJUY4?t=44' heldReason: rights - ordinal: 2 text: null startSeconds: 122 endSeconds: 133 watch: 'https://liquidgold.cc/watch/8aVbXXvJUY4?t=122' heldReason: rights - ordinal: 3 text: null startSeconds: 133 endSeconds: 190 watch: 'https://liquidgold.cc/watch/8aVbXXvJUY4?t=133' heldReason: rights - ordinal: 4 text: null startSeconds: 201 endSeconds: 254 watch: 'https://liquidgold.cc/watch/8aVbXXvJUY4?t=201' heldReason: rights - ordinal: 5 text: null startSeconds: 264 endSeconds: 341 watch: 'https://liquidgold.cc/watch/8aVbXXvJUY4?t=264' heldReason: rights - ordinal: 6 text: null startSeconds: 351 endSeconds: 383 watch: 'https://liquidgold.cc/watch/8aVbXXvJUY4?t=351' heldReason: rights - ordinal: 7 text: null startSeconds: 341 endSeconds: 351 watch: 'https://liquidgold.cc/watch/8aVbXXvJUY4?t=341' heldReason: rights - ordinal: 8 text: null startSeconds: 395 endSeconds: 430 watch: 'https://liquidgold.cc/watch/8aVbXXvJUY4?t=395' heldReason: rights - ordinal: 9 text: null startSeconds: 474 endSeconds: 506 watch: 'https://liquidgold.cc/watch/8aVbXXvJUY4?t=474' heldReason: rights - ordinal: 10 text: null startSeconds: 506 endSeconds: 518 watch: 'https://liquidgold.cc/watch/8aVbXXvJUY4?t=506' heldReason: rights - ordinal: 11 text: null startSeconds: 550 endSeconds: 561 watch: 'https://liquidgold.cc/watch/8aVbXXvJUY4?t=550' heldReason: rights - ordinal: 12 text: null startSeconds: 608 endSeconds: 640 watch: 'https://liquidgold.cc/watch/8aVbXXvJUY4?t=608' heldReason: rights - ordinal: 13 text: null startSeconds: 675 endSeconds: 686 watch: 'https://liquidgold.cc/watch/8aVbXXvJUY4?t=675' heldReason: rights - ordinal: 14 text: null startSeconds: 708 endSeconds: 720 watch: 'https://liquidgold.cc/watch/8aVbXXvJUY4?t=708' heldReason: rights - ordinal: 15 text: null startSeconds: 740 endSeconds: 750 watch: 'https://liquidgold.cc/watch/8aVbXXvJUY4?t=740' heldReason: rights - ordinal: 16 text: null startSeconds: 792 endSeconds: 825 watch: 'https://liquidgold.cc/watch/8aVbXXvJUY4?t=792' heldReason: rights - ordinal: 17 text: null startSeconds: 835 endSeconds: 867 watch: 'https://liquidgold.cc/watch/8aVbXXvJUY4?t=835' heldReason: rights - ordinal: 18 text: null startSeconds: 878 endSeconds: 931 watch: 'https://liquidgold.cc/watch/8aVbXXvJUY4?t=878' heldReason: rights - ordinal: 19 text: null startSeconds: 967 endSeconds: 980 watch: 'https://liquidgold.cc/watch/8aVbXXvJUY4?t=967' heldReason: rights --- # An Interaction Is All You Need — Ivan Leo, Google DeepMind Models became agents, and the APIs didn't keep up. Google DeepMind rebuilt them. Ivan Leo, developer experience engineer at Google DeepMind, introduces the Gemini Interactions API and Managed Agents. He traces how we went from single completions to function calling to agents, then shows server-side state with interaction IDs (no more hand-managing thought signatures), strongly typed multimodal outputs, mixing built-in and custom tools, and the new steps data model. He then demos Managed Agents, which run the Antigravity harness in a persistent remote sandbox with environment IDs, loadable sources, a credential-injecting proxy and named agents, plus the open-source Gemini API CLI. In this talk: • Why agent workloads need a different API shape • Server-side state: interaction IDs and thought signatures • Chaining image, video and audio generation with the same context • Managed Agents: persistent sandboxes, skills, secure credentials and named agents SPEAKER Ivan Leo, Developer Experience Engineer, Google DeepMind LinkedIn: https://www.linkedin.com/in/ivanleo X: https://x.com/ivanleomk GitHub: https://github.com/ivanleomk Website: https://ivanleo.com/ LINKS Interactions API overview: https://ai.google.dev/gemini-api/docs/interactions-overview Managed Agents quickstart: https://ai.google.dev/gemini-api/docs/managed-agents-quickstart Antigravity agent: https://ai.google.dev/gemini-api/docs/antigravity-agent Gemini API CLI (GitHub): https://github.com/google-gemini/gemini-api-cli Google AI Studio: https://ai.google.dev/aistudio CHAPTERS 0:00 Intro 0:12 Interactions API and Managed Agents 0:27 From single completions to agents 1:02 Function calling 1:32 Models that reason and act 2:02 What is an agent? 3:02 Try the models in AI Studio 4:07 Why a new API 5:31 Server-side state and thought signatures 6:21 Demo: chaining image and video generation 7:01 How the code works 7:36 Strongly typed outputs 8:21 Mixing built-in and custom tools 9:01 The steps data model 9:46 Managed Agents: Antigravity in the cloud 10:36 Demo: analyzing a GitHub repo 11:06 Persistent sandboxes with environment IDs 11:41 Loading sources: GCS, GitHub, inline files 12:16 A 2M-token repo analysis 12:56 The same agent locally and in the cloud 13:36 A credential-injecting proxy 14:26 Named agents 15:26 The Gemini API CLI 15:56 Migrating with the Interactions API skill 16:36 Wrap-up Recorded at the AI Engineer World's Fair 2026 in San Francisco. Subscribe for more talks from the engineers building with AI. AI Engineer: https://ai.engineer YouTube: https://www.youtube.com/@aiDotEngineer X: https://x.com/aiDotEngineer LinkedIn: https://www.linkedin.com/company/aidotengineer/ #Gemini #AIAgents #AIEngineer Canonical: https://liquidgold.cc/channel/aidotengineer/explore/video/an-interaction-is-all-you-need-ivan-leo-google-deep-07e67a47b3fd · Channel: [AI Engineer](https://liquidgold.cc/channel/aidotengineer.md) > Search chunk text is held until public-source provenance is verified. ## Document chunks --- #### Chunk 0: Document excerpt (0:12 to 1:39) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 1: Document excerpt (1:39 to 2:13) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 2: Document excerpt (2:13 to 3:21) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 3: Document excerpt (3:21 to 4:24) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 4: Document excerpt (4:24 to 5:51) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 5: Document excerpt (5:51 to 7:10) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 6: Document excerpt (7:10 to 7:54) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 7: Document excerpt (7:54 to 8:38) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 8: Document excerpt (8:38 to 9:21) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 9: Document excerpt (9:21 to 10:08) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 10: Document excerpt (10:08 to 11:15) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 11: Document excerpt (11:15 to 12:20) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 12: Document excerpt (12:20 to 13:12) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 13: Document excerpt (13:12 to 14:27) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 14: Document excerpt (14:27 to 15:42) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 15: Document excerpt (15:42 to 17:04) > Held: transcript rights do not permit this chunk's text.