Skip to content

07-deployment-and-production-operations.md

Latest commit

 

History

History
52 lines (33 loc) · 2.05 KB

07-deployment-and-production-operations.md

File metadata and controls

52 lines (33 loc) · 2.05 KB
layout default
title Chapter 7: Deployment and Production Operations
nav_order 7
parent ADK Python Tutorial

Chapter 7: Deployment and Production Operations

Welcome to Chapter 7: Deployment and Production Operations. In this part of ADK Python Tutorial: Production-Grade Agent Engineering with Google's ADK, you will build an intuitive mental model first, then move into concrete implementation details and practical production tradeoffs.

This chapter covers production packaging and run operations for ADK projects.

Learning Goals

  • choose deployment targets by workload profile
  • package and version agent services cleanly
  • add observability and rollback practices
  • operate with security and governance controls

Deployment Paths

  • local or containerized services for team workflows
  • Cloud Run style deployments for managed scaling
  • Vertex AI Agent Engine paths for enterprise integration

Operational Checklist

  • pin dependency and model configuration
  • capture invocation and tool telemetry
  • define rollback and incident response runbooks
  • enforce change approval for risky tool actions

Source References

Summary

You can now move ADK agents from prototype into production operations with clearer controls.

Next: Chapter 8: Contribution Workflow and Ecosystem Strategy

Source Code Walkthrough

google/adk/cli/ and server entrypoints

Deployment entry points are in google/adk/cli/. The CLI module exposes the adk deploy and adk web commands that translate a local agent project into a running service. Tracing the server startup and request handling in the CLI shows the production deployment path — how ADK wraps an agent in an HTTP endpoint suitable for Cloud Run or App Engine.