# Build Your Own Team of Managed Agents - Jack Wotherspoon, Google DeepMind

## Executive summary

Gemini Managed Agents allow developers to run sophisticated coding agents in secure, scalable cloud sandboxes via a single API call, eliminating the need for complex local infrastructure setup. This architecture enables robust, multi-agent workflows—such as sequential financial research and reporting—by sharing a persistent environment state across different agents. The system is built around the Interactions API and includes advanced features like secure credential proxies and scheduled triggers.

## Key takeaways

- Cloud Execution for Scalability and Security: Running agents in a cloud sandbox (Google Cloud infrastructure) solves local machine limitations, such as scaling constraints and browser interference. A dedicated proxy layer ensures that sensitive credentials (e.g., GitHub tokens) never enter the sandbox, only being injected when needed for specific API calls.
- Simplified Development via Interactions API: The Interactions API is the new agent-first SDK, replacing older model-input/output structures. It allows agents to perform multi-step actions, including writing files and calling custom MCP tools, all through a single API call.
- Multi-Agent Workflows through Shared Environments: Managed agents support complex workflows by allowing multiple agents to share the same environment ID (the sandbox file system). This enables one agent to perform research and save files, which a subsequent, different agent can then pick up and build upon, maintaining context and state.

## Technical details

- Managed Agent Architecture: Managed agents utilize a cloud sandbox and the Anti-Gravity harness. Key building blocks include: the **Harness** (Anti-Gravity, managing tool calls); the **Environment** (the stateful file system in the cloud); **Skills** (uploadable custom logic); **Credentials** (secure injection of OAuth/tokens via a proxy); and **Triggers** (allowing scheduled execution or webhooks).
- Advanced Model Capabilities: The platform supports tuning the agent using different models (e.g., Gemini Flash for speed, Gemini 4 Argon for deep reasoning/finance). Gemini 4 also features a long decode capability, expanding the context window up to 1 million tokens, which is shared across input, thinking, and output.
- Interactions and Environments Primitives: These two core primitives manage state: **Interactions** manage the conversation history (input/output turns), while **Environments** manage the actual file system state within the sandbox. Passing the Environment ID between agents allows for stateful, multi-step processes.

## Practical implications

- Build complex, automated workflows (e.g., SEC filing research $ ightarrow$ quant analysis $ ightarrow$ report generation) that are easily integrated into internal services or published externally.
- Use the system's API to create and save refined agents (using `agents.create`) for repeatable, controlled tasks.
- Implement scheduled tasks or webhooks by setting up managed agents with Triggers, enabling automated daily briefings or data checks.

## Topics

Managed Agents, Cloud Computing, AI Agents, Interactions API, Multi-Agent Systems, Workflow Automation, AI Studio, Gemini API

Source: https://www.youtube.com/watch?v=Y_p3y6zP5QE