# An Interaction Is All You Need — Ivan Leo, Google DeepMind

## Executive summary

Ivan Leo introduces the Gemini Interactions API and Managed Agents, addressing the architectural gap between simple model completions and complex, multi-step agentic workloads. The new APIs enable robust, stateful, and multimodal pipelines by introducing the `interaction ID` for context preservation and the `environment ID` for persistent, remote sandboxes. This allows developers to build sophisticated agents that can autonomously reason, use mixed tools, and handle complex data types (image, video, audio) without managing underlying infrastructure.

## Key takeaways

- State Management via Interactions API: The new API uses a persistent `interaction ID` to maintain context across multiple API calls, replacing the difficulty of manually managing thought signatures and ensuring performance consistency with the Gemini series of models. (5:31)
- Persistent Remote Sandboxes (Managed Agents): Managed Agents utilize the Anti-Gravity harness to provide persistent, remote sandboxes via an `environment ID`. This eliminates the need for developers to manage infrastructure or context preservation between agent runs. (9:01)
- Advanced Multimodality and Tooling: The API supports chaining different modalities (image, video, audio) and mixing built-in tools (e.g., Google Search) with custom tools in a single, complex workflow, all managed by the new steps data model. (6:21, 8:21)
- Security and Scalability: Security is enhanced with a man-in-the-middle proxy that intercepts outbound calls, preventing credential leakage even if the model is prompt-injected. The system supports up to 1,000 named agents without additional storage costs. (11:20)

## Technical details

- Interactions API: Designed for agent workloads, it supports complex, multi-step processes that go beyond single completions. Key features include the `interaction ID` for state preservation and the ability to handle multimodal outputs (audio, video, image) through strongly typed output structures. (5:31, 7:36)
- Managed Agents & Anti-Gravity: Provides a standardized, persistent remote sandbox environment. Developers use the `environment ID` to maintain state, allowing agents to autonomously research and process large repositories (e.g., analyzing a custom DSL repository). (9:01)
- Data Modeling: The new steps data model replaces the legacy outputs array, providing a clear, structured view of complex, asynchronous tool calls, model outputs, and thought signatures. (10:00)
- Security Mechanism: A man-in-the-middle proxy is implemented to secure outbound API calls, ensuring that sensitive credentials (like GitHub API tokens) are never exposed to the model, even in the event of a prompt injection attack. (11:20)

## Practical implications

- Build complex, multi-stage agentic applications that require persistent state and context across multiple API calls.
- Develop secure agents by leveraging the man-in-the-middle proxy to prevent credential leakage.
- Prototype and test agents locally using the open-sourced Gemini API CLI before deploying to the cloud.
- Scale agent deployments by utilizing up to 1,000 named agents within the Managed Agents framework.
- Simplify multimodal pipelines by using strongly typed output structures for audio, video, and image generation.

## Topics

Gemini API, Agentic Workflows, State Management, Multimodality, Server-Side Architecture, Anti-Gravity, Build Automation, Interactions API overview, Managed Agents quickstart, Anti-Gravity agent, Gemini API CLI, Google AI Studio

Source: https://www.youtube.com/watch?v=8aVbXXvJUY4