Create custom test case

​

Prompt our AI agent to generate new tests

If you want to translate a custom user flow into a test, you can have it AI generated from your prompt. Give us a short prompt and we deploy our AI agent to find the interactions leading towards your desired user flow.

While our AI agent generates the steps of your test cases, it informs you about its progress.

If the AI agent generated wrong steps or signals a failed step with a yellow alert, you can:

1. Restart the AI generation process by clicking regenerate steps. Select the last step you want to keep. All subsequent steps will be replaced with the new AI agent output.
2. Try a different prompt and restart the AI generation process by clicking regenerate steps.
3. Add, edit and remove steps manually. Our virtual locator picker helps you edit tests in no time. Learn how to edit test steps.

​

Pre-prompted login test

If your app has a login functionality that wasn’t AI auto-generated during set-up, we have a pre-prompted login test case for you. You can trigger it after giving us test user credentials.

Go to settings a.k.a. the gear icon in the upper right corner and select test account. Add test user credentials we can use to run the login test.

Or check out this video instead:

​

Chaining tests

A user flow is virtually a chain of test cases. When using the AI agent, you can use a dependency to chain test cases together. Shorter flows are faster, more specific and more reliable.

We fill in some dependencies for you set-up Octomind. These are the cookies banner test (in case your site has a cookie banner) and required login test if you need to be logged in to operate the app. You can keep, remove or add other dependencies if you wish.

This is how you do it:

• Give us a path where the AI agent should start its test case generation process, e.g. /products/
• Select a test case that should run before the AI agent is about to run.

​

Free prompting best practices

1. Keep prompts short and to the point.

2. Mention all steps required, e.g. if you have to click away a cookie banner, mention it.

   • Example without a cookie banner: sign in using username $OCTO_USERNAME and password $OCTO_PASSWORD
   • Example with a cookie banner: accept cookies then sign in using username $OCTO_USERNAME and password $OCTO_PASSWORD

3. You have access to the following template variables that we will fill for you, so just use them in the prompt as they appear here and in the example above. (You can also use these when manually editing a step).

   • $OCTO_USERNAME: The username you configured for use with your page in the sign up flow or the settings
   • $OCTO_PASSWORD: The password you configured for use with your page in the sign up flow or in the settings
   • $OCTO_URL: The URL of your page
   • $OCTO_STABLE_UUID: A random combination of letters and numbers that will be consistent through multiple references across a single run, but different if you run the agent again

4. These are the limitations so far:

   • We can only handle flows which happen inside the app. Cross-app or cross-device flows are not supported, e.g. we do not cover email confirmation flow yet.
   • We cannot handle captchas yet, unless it’s avoidable via custom headers
   • Our AI Agent might get blocked by robot detection on some high traffic sites. Sites / apps in production are more bot-protected than staging / test systems.
   • Our Agent is blocked by rate limiter. This is how you mitigate rate limitation.
   • The Agent might not support required type of interaction & assertion yet. Manual intervention will be necessary.
   • Timing and hydration issues can cause the Agent to fail, too.

​

Record a test case

For more manual control and for cases that the AI model struggles with, we have an option to enter code directly.

You can use the recorder to record steps for your test case. You can either start from scratch or start from a prompt or existing steps unsing the record from here button.

​

How is the Octomind recorder different from Playwright Codegen?

The recorder is a feature that allows you to record steps for your test case. It is different from Playwright Codegen in that it is a tool that allows you to control what step to record. It works based on snapshots that represent the current state of the page.

For example, when you choose an element to interact with, the recorder will only record the interaction and change the browsers state when you click the record the next step button. This allows correcting either the element or the interaction type. You can also record assertions to validate the state of the page.

You can first define the element to interact with. Then you can choose the interaction type. This way you have fine control over what interaction to record. This is especially useful when you want to record for instance hovering or drag’n’drop.

The interaction will only executed when you click the record the next step button. The browser will then move forward and the recorder presents the next snapshot after the interaction was executed.