
Before you begin
- Labs create a Google Cloud project and resources for a fixed time
- Labs have a time limit and no pause feature. If you end the lab, you'll have to restart from the beginning.
- On the top left of your screen, click Start lab to begin
Getting started with Conversational Agents
/ 30
Import a .blob virtual agent file
/ 10
Testing in the Draft environment
/ 20
Testing in the QA environment
/ 20
Testing in the Dev environment
/ 20
Most businesses go through different phases of project development and production cycles. Effective maintainance of these projects require systems and processes to manage versions and environments. Conversational Agents provides tools within the UI for managing multiple versions and loading specific versions to dedicated environments, which allows usage for different purposes (and perhaps by different teams). In this lab you'll explore the management of Conversational Agents versions and environments.
The following are definitions of versions and environments with respect to Conversational Agents.
Draft
, where all changes are made to an agent using the Conversational Agents user interface. To load a virtual agent you've modified in the Draft environment to another environment, you'll need to first establish a version of it.By the end of this lab, you will be able to:
This lab uses the basic Flight Booker agent developed in Conversational Agents: Bot Building Basics and assumes basic knowledge of Conversational Agents such as using the Test Simulator and how intents, flows, and pages work.
Read these instructions. Labs are timed and you cannot pause them. The timer, which starts when you click Start Lab, shows how long Google Cloud resources are made available to you.
This hands-on lab lets you do the lab activities in a real cloud environment, not in a simulation or demo environment. It does so by giving you new, temporary credentials you use to sign in and access Google Cloud for the duration of the lab.
To complete this lab, you need:
Click the Start Lab button. If you need to pay for the lab, a dialog opens for you to select your payment method. On the left is the Lab Details pane with the following:
Click Open Google Cloud console (or right-click and select Open Link in Incognito Window if you are running the Chrome browser).
The lab spins up resources, and then opens another tab that shows the Sign in page.
Tip: Arrange the tabs in separate windows, side-by-side.
If necessary, copy the Username below and paste it into the Sign in dialog.
You can also find the Username in the Lab Details pane.
Click Next.
Copy the Password below and paste it into the Welcome dialog.
You can also find the Password in the Lab Details pane.
Click Next.
Click through the subsequent pages:
After a few moments, the Google Cloud console opens in this tab.
In this task, you log in to Conversational Agents and create the new virtual agent Flight Booker - Env Mgt
.
Assumption: You've already logged into Google Cloud before continuing with the steps below.
In a new incognito window, go to the Conversational Agents page.
In the Select Project dialog, click the All tab.
Click your Project ID,
In the Google Dialogflow API dialog, — click "Enable API" to proceed.
In the Agents window, click Create agent.
Click Build your own.
In the Create agent dialog, set the following fields:
Field | Value |
---|---|
Display name | Flight Booker - Env Mgt |
Location | |
* Time zone | Select the GMT offset that applies to the selected location |
Conversation Start | Select Flow |
Click Create.
Once you create the agent, the Default start flow window opens.
After creating the agent, navigate to Settings > General > Logging settings and click Enable Cloud Logging and Enable conversation history. This generates logs for this agent.
Click Save.
Click Check my progress below to verify you're on track in this lab.
Import the virtual agent from the earlier lab, Conversational Agents: Bot Building Basics
, and use it to explore the environment functionality:
Click the following link to download the sample lab 1 virtual agent solution, gsp929-start-agent, to your local hard drive.
On the Agent Overview page, click the Export/Restore button.
Select Restore Agent from the expanded menu options.
Select the Upload radio button.
Click on select file.
Navigate to and select the gsp929-start-agent.blob that you downloaded to your hard drive.
Click Open.
Click Restore.
Refer to the Conversational Agents 'restore' documentation as needed.
Now you have a virtual agent that has everything completed from the earlier lab.
Click Check my progress below to verify you're on track in this lab.
Notice there is an Environment dropdown.
By default, you should see Draft
in this dropdown because you haven't yet created any other environment.
Notice there is a second dropdown for Start Resource.
By default, you should see Flow
in this dropdown because no other flows exist. You could select Default Start Flow
, but it isn't necessary at this point.
In the Talk to agent box, type "i want to book a flight".
The next response from the agent should be, 'What city would you like the flight to depart from?'
Notice the data at the top of the conversation that shows Flow: Default Start Flow
.
You may have noticed some of this while completing the earlier lab. Now you'll need to pay closer attention to what's selected in the dropdowns as you move forward through this lab.
Click Check my progress below to verify you're on track in this lab.
Click + Create to create a new environment.
Enter 'QA' for the Display Name.
Click Save.
Click x to dismiss the environment creation error message.
Select Versions in the main menu.
Under Flows tab, click Default Start Flow.
Click + Create to create a version of the flow.
For the Display name field enter 'Flight booker main v1 chat bot' .
Enter a description in the description box on what's included in this version of the virtual agent.
Click Save.
You should now see the Default Start Flow
in the Versions list with the # versions
, equal to 1.
Notice whether the status shows Not ready or Ready.
Select Environments to reattempt configuring a new environment.
Click + Create.
Enter 'QA' for the Display Name.
In the Flow section, choose Flight booker main v1 chat bot
from the Version dropdown list next to the Default Start Flow. Recall that this didn't exist in the dropdown earlier.
Click Save.
Version 'projects/qwiklabs-gcp-03-407df58d36b0/locations/ //agents/e2779218-b813-4844-a0ea-ec2ef504636d/flows/00000000-0000-0000-0000-000000000000/versions/1' is not ready to serve because its training is RUNNING. Wait for training to finish or fix the version if its training failed.
This is caused when Conversational Agents is still capturing and training your versioned agent. Do you remember if the status of the version creation showed Not ready? Try saving again after waiting a few moments for the version creation status to change to Ready.
You should now see your new QA environment in the list with a Last modified date.
Next, you can test out your versioned virtual agent in the environment you created.
To test the agent, click on Toggle Simulator in the upper-right corner to open it if it's not already open.
Click the "Reset conversation" button in the Test Agent pane if there is a simulator from previous tests.
Select QA from the Environment dropdown.
In the Talk to agent box, enter 'i want to book a flight'.
This is one of the ways you can run test cases in different environments. However, you may be thinking, if the version loaded to QA is the same as what's in Draft, testing will produce the same results. You're right. Next you'll make a change that makes it more obvious.
Click Check my progress below to verify you're on track in this lab.
Next you'll make a change to your virtual agent, save it as a new version, and load it to a new environment.
Click on Edit fulfillment to edit the entry fulfillment information.
To add a response, click +Add dialogue response, then select Agent dialogue under Agent responses. In the Enter Agent Dialogue box, type the prompt: 'I'll be happy to assist you with that.'
Click Add and Save.
At this point, you've saved the change to your working draft. Next you'll create a new version of the virtual agent that includes this change.
Go back to Versions.
Under Flows tab, click the Default Start Flow to begin the process of creating a new version for it.
Repeat the versioning steps above to create a new version of your Default Start Flow called 'Flight booker main v2 chat bot'.
Add a description, such as 'Version 2 adds a friendly greeting before prompting for flight details'.
Click Save.
You should now see number of versions incremented to 2 for the Default Start Flow in the Versions list.
Repeat the steps you followed above to create a new environment called 'Dev' that uses the new version 2 of your Default Start Flow.
Select your Flight booker main v2 chat bot
from the version dropdown.
Click Save.
Version 'projects/qwiklabs-gcp-00-fe6cab958249/locations/ /agents/6792c492-5f79-4ccf-8f17-e757b34f38b9/flows/00000000-0000-0000-0000-000000000000/versions/2' is not ready to serve because its training is RUNNING. Wait for training to finish or fix the version if its training failed.
Now your latest version of your flow is loaded to the Dev environment.
Next you'll go back to the simulator to test your new Flight booker main v2 chat bot
version.
Open the Test Agent pane if not open already.
Click the Reset conversation button in the Test Agent pane if there is a simulator from previous tests.
From the Environment dropdown select Dev.
Type 'i want to book a flight' into the Talk to agent box.
You should get a response from the agent saying, I'll be happy to assist you with that.
, followed by a prompt for the departure city. This indicates that it's running the v2 version of your agent.
Click Check my progress below to verify you're on track in this lab.
You've created two environments now and loaded a different version into each. What if you need to change the version loaded into one of those environments?
Click on Environments in the left pane as needed to get to the view of both of your environments, QA and Dev.
Click on the QA
environment.
Select Flight booker main v2 chat bot
from the version dropdown.
Click Save.
Notice the Last modified
time for the version.
Use the test simulator to ensure the version two is loaded. (Recall that you added the friendly greeting to this one.) Don't forget to click "Reset conversation" to begin a fresh test scenario and choose QA in the environment dropdown.
Go back and load Flight booker main v1 chat bot
to the QA environment.
Retest. Was it what you expected? You should no longer see the friendly greeting prior to the prompt for departure city.
Discuss your working environment - What version of your agent do you suppose would be tested if you ran the test simulator using the Draft environment? You guessed it! The working copy that you've recently saved or uploaded. You can test the working copy of your virtual agent in Draft until you're ready to create a version of it. At that point, you could save it to another environment so that another team can begin testing that frozen version.
By selecting a specific environment, the test is running the version of your virtual agent loaded to the specified environment (which may be different from what you're currently working on in Conversational Agents in Draft mode). Another benefit is you can test different versions without going through the process of retraining the model (which can take some time for larger, more complex virtual agents).Before you sign out, you can to export your virtual agent if you want. Recall that this is done through the following general steps:
Select View all agents
from the Agent dropdown at the top.
Click on the context menu (three vertical dots) and choose Export.
Click on the Download radio button.
Click Export.
Now you can manage different versions of a virtual agent and run tests in different environments.
...helps you make the most of Google Cloud technologies. Our classes include technical skills and best practices to help you get up to speed quickly and continue your learning journey. We offer fundamental to advanced level training, with on-demand, live, and virtual options to suit your busy schedule. Certifications help you validate and prove your skill and expertise in Google Cloud technologies.
Manual last updated July 21, 2025
Lab last tested July 21, 2025
Copyright 2025 Google LLC. All rights reserved. Google and the Google logo are trademarks of Google LLC. All other company and product names may be trademarks of the respective companies with which they are associated.
This content is not currently available
We will notify you via email when it becomes available
Great!
We will contact you via email if it becomes available
One lab at a time
Confirm to end all existing labs and start this one