# 7 Things Your AI Coworker Needs - Philipp Schmid, Google DeepMind

## Executive summary

Philipp Schmid details the architecture for building autonomous AI coworkers using Gemini and Managed Agents. The system is designed to function as a digital employee, requiring seven core components: a brain (Gemini), a computer (Managed Agents sandbox), playbooks (skills), tools (MCP servers), secure credentials, house rules (hooks), and schedules (triggers). The use of a network proxy for credentials and deterministic hooks significantly enhances security and control, allowing the agent to perform complex, scheduled tasks like automated portfolio audits.

## Key takeaways

- Autonomous Agent Architecture: An AI coworker requires seven components: a brain, a computer, playbooks, tools, credentials, house rules, and a schedule. Managed Agents provide the necessary remote sandbox for the agent to run code and tools.
- Managed Agents for Sandboxing: Managed Agents simplify agent creation by providing a remote sandbox, eliminating the complex tool-calling loop. The agent can execute code (e.g., writing a file) directly via an API call within the managed environment.
- Enhanced Security with Network Proxy: Credentials are secured using an external network proxy. This proxy swaps dummy credentials with real ones only for explicitly defined domains, making it impossible for a prompt injection attack to steal sensitive keys.
- Deterministic Guardrails via Hooks: Hooks allow for deterministic control over the agent's decisions. By defining a matcher (regex) on tool calls, human approval can be required for specific actions, ensuring compliance and safety.

## Technical details

- Gemini Model Capabilities: Gemini 4 Argon offers up to 1 million unified context tokens, with strong improvements in math and reasoning, providing more than 64K tokens for complex thinking and proof work.
- Managed Agents Implementation: To create an agent (e.g., 'Bug'), one defines the agent ID, uses the agent harness, and specifies the model. The environment can be bootstrapped using skills defined in an `agents.md` file or a connected GCS bucket.
- Tooling and Integration: Tools include built-in skills (Google Search), or external services accessed via an MCP server (e.g., Gmail, Spreadsheets). Custom functions can be provided for agentic capabilities outside the sandbox.
- Scheduling and Triggers: Agents can be made proactive using basic cron triggers (e.g., running an audit every 30 days at 8:00 a.m.). Webhooks are also supported for connecting external services (like SAC providers) to trigger agent actions.

## Practical implications

- Build engineers can implement highly secure, autonomous workflows that mimic human employees, moving beyond simple chatbot interactions.
- The architecture provides clear separation of concerns: Gemini for reasoning, Managed Agents for execution, and external services for data/credentials.
- The use of network proxies and hooks allows for building 'trustworthy' agents, which is critical for enterprise integration and compliance.

## Topics

Autonomous Agents, Gemini API, Managed Agents, Workflow Automation, Security Architecture, Cron Triggers, AI Engineering, AI Studio, Gemini 4 Argon

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