The Tool Desk
Outbyte PC Repair FREERepair Windows errors before they cause bigger problemsFix Now →Outbyte Driver Updater FREEFix the driver behind crashes, sound loss and screen glitchesFind Drivers →iTechGuides is reader-supported. When you buy through links on our site, we may earn an affiliate commission. As an Amazon Associate I earn from qualifying purchases. Learn more
This guide shows how to build and deploy a custom work agent with Google Cloud’s Agent Development Kit (ADK) and Agent Runtime, documented under Gemini Enterprise Agent Platform. It follows Google’s code-first Python quickstart; it does not cover every Gemini product or a prebuilt work assistant.
Choose an agent-building path
Google Cloud documents several ways to build agents, including visual, low-code Agent Studio; the Managed Agents API; and code-first development with ADK or other frameworks. This guide uses ADK with the Python Agent Platform SDK because Google provides a specific build, deploy, and test quickstart for that route. Choose a different path if your team needs visual authoring, a managed-agent interface, another framework, or a different language.
Deployment options also differ by language, release workflow, staging requirements, and control over the server or container. Choose the route before installing dependencies so your development setup matches the way your team will release the agent.
Prepare the Google Cloud project
Select a project and confirm billing
- In the Google Cloud console, select a project you can access, or create one. Creating a project requires Project Creator (
roles/resourcemanager.projectCreator); selecting an existing project shared with you does not require a special project-selection role. - Confirm that billing is enabled for the project before deploying.
- Enable the APIs required by your chosen deployment route. Google’s current environment setup page lists Gemini Enterprise Agent Platform, Cloud Storage, Cloud Logging, Cloud Monitoring, Telemetry, Cloud Trace, and Resource Manager APIs for the documented runtime environment. The ADK quickstart describes enabling Agent Platform and Cloud Storage APIs for its quickstart, so check the current instructions for the actual route rather than relying on an older API checklist.
Enabling APIs requires serviceusage.services.enable. If you cannot enable them, ask an administrator for that permission or the Service Usage Admin role (roles/serviceusage.serviceUsageAdmin). Google’s [c001] and [c002] documentation covers project setup and the quickstart prerequisites.
#1 Best Overall
- Alexa can show you more - Echo Show 5 includes a 5.5” display so you can see news and weather at a glance, make video calls, view compatible cameras, stream music and shows, and more.
- Small size, bigger sound – Stream your favorite music, shows, podcasts, and more from providers like Amazon Music, Spotify, and Prime Video—now with deeper bass and clearer vocals. Includes a 5.5" display so you can view shows, song titles, and more at a glance.
- Keep your home comfortable – Control compatible smart devices like lights and thermostats, even while you're away.
- See more with the built-in camera – Check in on your family, pets, and more using the built-in camera. Drop in on your home when you're out or view the front door from your Echo Show 5 with compatible video doorbells.
- See your photos on display – When not in use, set the background to a rotating slideshow of your favorite photos. Invite family and friends to share photos to your Echo Show. Prime members also get unlimited cloud photo storage.
Request runtime access and plan agent identity
Google lists Agent Platform User (roles/aiplatform.user) as the project role for using Agent Runtime. API-enablement permission is separate. Agent Runtime has a default Reasoning Engine service agent, and Google also documents agent identity and custom service-account options for more granular access. Decide what services the work agent must reach, then grant only the permissions needed; cross-project access may require additional configuration. See Google’s environment setup guidance for IAM and service identity details.
Set up ADK and define the work agent
Create an isolated Python environment
Google’s ADK quickstart sequence is to install the Agent Platform SDK for Python and ADK, create an example agent, deploy it, and test it. Use a virtual environment to isolate dependencies. Package commands and SDK versions can change, so follow the current commands on Google’s ADK quickstart rather than copying an old version pin. For reproducible deployments, Google recommends pinning package versions and keeping dependencies minimal.
Rank #2
- Alexa can show you more - Echo Show 5 includes a 5.5” display so you can see news and weather at a glance, make video calls, view compatible cameras, stream music and shows, and more.
- Small size, bigger sound – Stream your favorite music, shows, podcasts, and more from providers like Amazon Music, Spotify, and Prime Video—now with deeper bass and clearer vocals. Includes a 5.5" display so you can view shows, song titles, and more at a glance.
- Keep your home comfortable – Control compatible smart devices like lights and thermostats, even while you're away.
- See more with the built-in camera – Check in on your family, pets, and more using the built-in camera. Drop in on your home when you're out or view the front door from your Echo Show 5 with compatible video doorbells.
- See your photos on display – When not in use, set the background to a rotating slideshow of your favorite photos. Invite family and friends to share photos to your Echo Show. Prime members also get unlimited cloud photo storage.
Specify the agent’s job and boundaries
Before connecting workplace data or tools, define the actual task, what information the agent may access, which actions it may take, and how it should respond when it cannot complete a request. The ADK quickstart uses a currency-exchange example to demonstrate the develop-deploy-test flow; it is a sample, not evidence that an agent is suitable for your work processes.
Recommended Free Tools
For deployment, the agent object and its tools need to be serializable. Google recommends separating initialization—such as loading models and setting up tools—from query execution. Framework templates can handle these lifecycle patterns. Review Google’s agent creation guidance before adding components that may not serialize cleanly.
Rank #3
- Google Nest Hub 1st Gen H1A – 7-inch smart display with Google Assistant built in for hands-free help, smart home control, entertainment, and daily organization.
- Korean Spec Model – International/Korean version of the Google Nest Hub H1A. Language can be changed to English after setup through the Google Home app/device settings.
- Smart Home Control – Use voice commands or the touchscreen to control compatible smart lights, cameras, thermostats, plugs, speakers, and other Google Assistant devices.
- Entertainment & Daily Help – Stream music, watch videos, view Google Photos, check weather, set timers, manage reminders, follow recipes, and get answers hands-free.
- Compact 7" Display Design – Great for kitchens, bedrooms, desks, offices, counters, and nightstands with a clean modern smart display design.
Choose a deployment method
Google documents multiple Agent Runtime deployment methods. The right choice depends on your team’s source-control and release workflow, language, need for server or image control, and whether the agent can be serialized.
| Method | Fits when | Constraints and staging |
|---|---|---|
| Developer Connect | You want deployment from a linked Git repository, with version control, collaboration, and CI/CD. | Python only; create the Developer Connect repository link first. |
| Source files | You want declarative or automated workflows, including CI/CD and infrastructure-as-code. | Python only; Google says this method does not require a Cloud Storage staging bucket. |
| Dockerfile | You need to define and control the API server in the deployed container. | Any language; the container must follow the Agent Runtime contract. |
| Container image | You want control over the image build and to reduce deployment latency. | Any language; the image must follow the Agent Runtime contract. |
| Agent Platform SDK object | You are developing interactively, including in Colab, and can deploy an in-memory local_agent. |
Best suited to agents without complex non-serializable structures; artifacts are staged in Cloud Storage. |
Google’s deployment documentation says Developer Connect and source-file deployment are Python-only; Dockerfile and container-image methods support any language. ADK itself is available in several languages, but that does not mean every Agent Runtime deployment method accepts every ADK language. Consult Google’s deployment methods page for route-specific details.
Account for Cloud Storage staging
Google says source-file deployment does not need a Cloud Storage bucket. Deploying an in-memory SDK agent object does use a bucket to stage artifacts, and the authenticated principal needs Storage Admin access to that bucket. Google recommends a bucket in the deployment project; for a bucket in another project, grant the Agent Platform service agent read access there.
Do these 3 things before closing this tab:
1Repair Windows errors before they cause bigger problems2Fix the driver behind crashes, sound loss and screen glitches3Clear out junk files and repair common Windows errorsDeploy and test the remote agent
- Use the deployment command or workflow for the route you selected, following Google’s current quickstart or deployment instructions.
- Test the deployed agent remotely with representative requests for its intended work task. Confirm that responses are appropriate and that required tools and permissions work.
- Use Google’s agent-evaluation guidance to assess behavior before relying on the agent in a production workflow. One successful response or completion of the sample quickstart does not establish production readiness.
Google’s Agents overview links to evaluation resources and additional development paths.
Best Value
- BUNDLE INCLUDES: Google Nest Hub Max with English, Spanish, French, Japanese and Global Language Compatibility so it works everywhere, Universal Power Adapter and Quick Start Guide with International Manual for Global Users
- IT WORKS EVERYWHERE Easy to use and will automatically start up in English when connecting to your device for the first time. The Nest Hub works globally with support for most languages and places internationally. And its language settings can always be changed back and forth to your preferred language anytime for international use or travel at your convenience
- BLENDS RIGHT INTO YOUR HOME Looks great on a nightstand, shelf, countertop - or the wall. This Nest Hub is small and mighty with bright sound that kicks! It plugs into the wall and is powered by the global ac adapter that works internationally so it works in outlets everywhere
Check costs before expanding use
The setup documentation reviewed here does not establish a workload-specific price or recurring Agent Runtime cost. Costs depend on the services and usage in your project, so check current Google Cloud pricing and billing information for your region and expected workload before deployment. Google’s quickstart advertises $300 in credits for new customers, but eligibility, expiration, and applicable terms should be confirmed on the current offer; it is not a general cost estimate.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
