Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions docs/analytics-modules-manual-test-overview.md
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@ keywords:
- test browser
- test OS
- test device coverage
url: https://www.lambdatest.com/support/docs/analytics-modules-resource-utilization/
url: https://www.lambdatest.com/support/docs/analytics-modules-manual-test-overview/
site_name: LambdaTest
slug: analytics-modules-manual-test-overview/
---
Expand All @@ -35,7 +35,7 @@ slug: analytics-modules-manual-test-overview/
"@type": "ListItem",
"position": 3,
"name": "Test Overview",
"item": "https://www.lambdatest.com/support/docs/analytics-modules-resource-utilization/"
"item": "https://www.lambdatest.com/support/docs/analytics-modules-manual-test-overview/"
}]
})
}}
Expand Down
2 changes: 1 addition & 1 deletion docs/bamboo-integration-with-hyperexecute.md
Original file line number Diff line number Diff line change
Expand Up @@ -90,7 +90,7 @@ cd ROOT_FOLDER
./bin/start-bamboo.sh
```

- Now type **http://localhost:8085/** in your browser to open the Bamboo GUI.
- Now type ``http://localhost:8085/`` in your browser to open the Bamboo GUI.

> **NOTE:** If you are running Bamboo for the very first time, then you need to configure the Setup Wizard as well. Follow the instructions [here](https://confluence.atlassian.com/bamboo/running-the-setup-wizard-289276851.html) to configure it.

Expand Down
2 changes: 1 addition & 1 deletion docs/concource-ci.md
Original file line number Diff line number Diff line change
Expand Up @@ -82,7 +82,7 @@ npm install npm@latest -g

---

4. Install Concourse and start a Concourse server at port 8080 i.e. *http://127.0.0.1:8080*.
4. Install Concourse and start a Concourse server at port 8080 i.e. ``http://127.0.0.1:8080``.

5. Install fly CLI tool for Concourse CI/CD. We recommend using the latest fly version, you can check the fly version using:

Expand Down
2 changes: 1 addition & 1 deletion docs/gocd-integration-with-hyperexecute.md
Original file line number Diff line number Diff line change
Expand Up @@ -75,7 +75,7 @@ Download or Clone the code sample from the LambdaTest GitHub repository to run t
```bash
./bin/go-agent start
```
- Now type **http://localhost:8153/go** in your browser to open the GoCD GUI.
- Now type ``http://localhost:8153/`` go in your browser to open the GoCD GUI.

- Click on the New Pipeline Button.

Expand Down
6 changes: 3 additions & 3 deletions docs/hyperexecute-qtest-integration.md
Original file line number Diff line number Diff line change
Expand Up @@ -52,7 +52,7 @@ This document details the seamless integration between HyperExecute and qTest, e

## Prerequisites

- You must have [Python 3.6](https://www.python.org/downloads/), [Apache Maven](https://maven.apache.org), and [Git](https://git-scm.com/download/) installed on your local machine.
- You must have [Python 3.6](https://www.python.org/downloads/), [Apache Maven](https://maven.apache.org), and [Git](https://git-scm.com/downloads) installed on your local machine.
- [Download](https://support-hub.tricentis.com/open?sys_kb_id=194a54eedb4f5c181ea7bb13f3961950&id=kb_article_view&number=KB0015571) and extract the **agentctl-[version]-mac-x64-full.tgz** file to a desired installation directory.
- Login to qTest Manager as an administrator and access the Resources page.
- Expand the **APIs and SDK** sections.
Expand All @@ -65,7 +65,7 @@ This document details the seamless integration between HyperExecute and qTest, e
./agentctl start
```

- Visit [http://localhost:6789](http://localhost:6789), add your details and click on the **Register** button.
- Visit ``http://localhost:6789``, add your details and click on the **Register** button.

- **Host Name :** You have to enter any name that will be assigned as the host name.
- **qTest URL :** Enter the URL of your qTest Manager page. For e.g. `https://aman.qtestnet.com`
Expand Down Expand Up @@ -138,7 +138,7 @@ You can download the CLI for your desired platform from the below mentioned link

## Step 3: Setup the Automation

- Navigate to your [Automation Host](http://localhost:6789/home) and click on the **Add** button to add a new agent.
- Navigate to your Automation Host ``http://localhost:6789/home`` and click on the **Add** button to add a new agent.

<img loading="lazy" src={require('../assets/images/hyperexecute/integration/products/qtest/1.png').default} alt="provide access to LambdaTest account" width="1280" height="684" className="doc_img"/>

Expand Down
104 changes: 104 additions & 0 deletions docs/kane-ai-web-test-writing-guidelines.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,104 @@
---
id: kane-ai-web-test-writing-guidelines
title: KaneAI Web Agent - Guidelines for Writing Instructions
hide_title: false
sidebar_label: Web Agent Instruction Guide
description: Learn how to write instructions for running the kane ai web agent smoothly and without any problem
keywords:
- lambdatest automation
- lambdatest kaneai
- kaneai Web test
- kaneai guidelines
- instructions writings
url: https://www.lambdatest.com/support/docs/kane-ai-web-test-writing-guidelines
site_name: LambdaTest
slug: kane-ai-web-test-writing-guidelines/
---

import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';

<script type="application/ld+json"
dangerouslySetInnerHTML={{ __html: JSON.stringify({
"@context": "https://schema.org",
"@type": "BreadcrumbList",
"itemListElement": [{
"@type": "ListItem",
"position": 1,
"name": "Home",
"item": "https://www.lambdatest.com"
},{
"@type": "ListItem",
"position": 2,
"name": "Support",
"item": "https://www.lambdatest.com/support/docs/"
},{
"@type": "ListItem",
"position": 3,
"name": "KaneAI Web Test",
"item": "https://www.lambdatest.com/support/docs/kane-ai-web-test-writing-guidelines"
}]
})
}}
></script>
The KaneAI Web Agent is an automation tool that executes web interactions based on natural language instructions. This guide provides best practices for writing clear, user-friendly instructions when using the KaneAI Web Agent. The goal is to ensure accurate execution of tasks by the AI and improve the quality of interactions with web elements.

## General Instruction

### 1. Clarity and Specificity
Always provide clear and specific instructions for the action you wish to perform. Use the appropriate terminology from the list of supported commands. Avoid vague terms such as `do this` or `click that`—be explicit about which element to interact with.

### 2. Context
When the action is dependent on a specific element or section of a webpage, provide enough context to help identify the element. Example: `Click the 'Submit' button on the top right corner of the form`.

### 3. Step-by-Step Instructions
Break down complex tasks into smaller, manageable steps. Use logical connectors like `then` or `after that` to indicate the sequence of actions. Clearly specify the flow, such as `Click 'Login', then type your email in the input field.`

### 4. Use Examples
Refer to the examples provided in the list of supported commands for guidance on structuring your instructions.
Example: `Type 'username' in the search bar and press 'Enter' to submit.`

### 5. Wait Command
Use the wait command when needed to pause execution, allowing operations or page loads to complete before proceeding to the next action. Example: `Click 'Submit' and wait for 5 seconds before proceeding to the next step.`

### 6. Refining Prompts
If the AI response is not as expected, refine your prompt by adding more details or increasing clarity. Use iterative refinement to achieve the desired outcome.

### 7. Tab Targeting
When interacting with elements that open in a new tab, use the prompt `switch to the <TabTitle> tab` to ensure actions stay on the newly opened tab.

## DO's & DON'Ts

### DO's
- **Specify the Exact Element :** Clearly indicate which element you want to interact with. For instance, use the element's name, position, or attributes.
Example: `Click on the second product in the list.`

- **Use Action Verbs :** Start your instructions with action verbs like "Click," "Type," "Hover," etc.
Example: `Hover over the navigation bar.`

- **Provide Context for Conditional Actions :** If the action depends on an element’s visibility or existence, include this in the instruction. Example: `If the 'Login' button is visible, click it.`

- **Use Numbers to Indicate Positions or Quantities :** When specifying positions or quantities, use numbers for clarity. Example: `Scroll down 100 pixels.`

- **Verify Steps Before Saving Test Cases :** Use the re-run option to ensure KaneAI executes all steps correctly and without errors before saving the test case.

- **Validate Test Flow While Editing :** Let the test run to validate if the flow is correct while editing a test case. Click "Resume" only after all steps are completed.

- **Use Manual Interaction When Necessary :** If KaneAI struggles to execute the desired action, manually intervene to guide the AI appropriately.

### DON'Ts
- **Avoid Vague Terms :** Do not use terms like "Click that" or "Do this" without specifying which element or action.

- **Do Not Assume Context Without Detail :** Ensure instructions are detailed enough for the AI to understand which elements are involved. Example of what to avoid: `Click the button" (without specifying which button)`.

- **Avoid Overloading Instructions :** Do not combine too many actions into a single instruction unless they are logically sequenced. Example of what to avoid: `Click the button and type in the field and then hover.`

- **Do Not Mix Unrelated Commands Without Logical Sequence :** Keep commands logically connected. Avoid mixing different actions without specifying the sequence. Example of what to avoid: `Click and then go to a new tab (without a clear sequence)`.

- **Always Verify Results for Assertions :** When using assertions, confirm that the expected result occurs to ensure success.

- **Acknowledge AI Limitations :** If the AI doesn’t perform the desired action, refine the prompt instead of expecting perfect results on the first try.

- **Use Iterative Approach for Accuracy :** Allow the AI to process, execute the action, and respond. If the initial outcome isn’t correct, refine and reissue the prompt iteratively.

- **Avoid Unnecessary Jargon :** Use simple language to communicate instructions. Only use technical terms when necessary.
2 changes: 1 addition & 1 deletion docs/local-testing-for-windows.md
Original file line number Diff line number Diff line change
Expand Up @@ -88,7 +88,7 @@ In a few seconds, after you execute the command, an SSH connection will be estab

<img loading="lazy" src={require('../assets/images/local-testing-for-windows/start-localhost-testing-using-lambda-tunnel.webp').default} alt="Image" className="doc_img"/>

> **IMPORTANT NOTE**: Some browsers doesn’t support automatic resolution of the URL string "localhost". Therefore if you test on URLs like "http://localhost/" or "`http://localhost:8080`" etc, you would get an error in these browsers. A possible solution is to use "localhost.lambdatest.com" or replace the string "localhost" with machine IP address. For example if you wanted to test "http://localhost/dashboard" or, and your machine IP is 192.168.2.6 you can instead test on "`http://192.168.2.6/dashboard`".
> **IMPORTANT NOTE**: Some browsers doesn’t support automatic resolution of the URL string "localhost". Therefore if you test on URLs like `http://localhost/` or "`http://localhost:8080`" etc, you would get an error in these browsers. A possible solution is to use "localhost.lambdatest.com" or replace the string "localhost" with machine IP address. For example if you wanted to test `http://localhost/dashboard` or, and your machine IP is 192.168.2.6 you can instead test on "`http://192.168.2.6/dashboard`".

## Testing Local Folder Files Using LambdaTest Tunnel
* * *
Expand Down
2 changes: 1 addition & 1 deletion docs/running-your-first-cypress-test.md
Original file line number Diff line number Diff line change
Expand Up @@ -93,7 +93,7 @@ Also in `run-settings` section you need to specify the path of your `spec.js` fi
```

:::info Note
In this demo, all occurrences of **http://localhost:8080** have been replaced with [https://example.cypress.io](https://example.cypress.io) to prevent running the Cypress tests locally. Alternatively, if you want to run your tests locally, refer to the [**Run locally**](https://www.lambdatest.com/support/docs/running-your-first-cypress-test/#running-your-cypress-tests-locally-on-lambdatest-platform) section below.
In this demo, all occurrences of ``http://localhost:8080`` have been replaced with [https://example.cypress.io](https://example.cypress.io) to prevent running the Cypress tests locally. Alternatively, if you want to run your tests locally, refer to the [**Run locally**](https://www.lambdatest.com/support/docs/running-your-first-cypress-test/#running-your-cypress-tests-locally-on-lambdatest-platform) section below.
:::

**Step-3:** Execute your tests using the following command in the terminal:
Expand Down
2 changes: 1 addition & 1 deletion docs/teamcity-with-hyperexecute.md
Original file line number Diff line number Diff line change
Expand Up @@ -60,7 +60,7 @@ To integrate TeamCity with HyperExecute, follow the below mentioned steps:
### Step 1: Start the TeamCity GUI

- Go to the **teamcity/bin** folder and run the command **./runAll.sh start** to start the TeamCity Server in your system.
- Now type **http://localhost:8111/** in your browser to open the TeamCity GUI.
- Now type ``http://localhost:8111/`` in your browser to open the TeamCity GUI.
- Click on Create Project button.

<img loading="lazy" src={require('../assets/images/hyperexecute/integration/ci-cd/teamcity/Step1.webp').default} alt="Image" className="doc_img"/>
Expand Down
22 changes: 11 additions & 11 deletions sidebars.js
Original file line number Diff line number Diff line change
Expand Up @@ -1013,27 +1013,27 @@ module.exports = {
"why-we-need-kane-ai",
"kane-ai-web-test",
"kane-ai-guided-walkthrough",
"kane-ai-app-test",
"kane-ai-test-plan"
],
},
{
type: "doc",
label: "App Test",
id: "kane-ai-app-test"
},
{
type: "doc",
label: "Test Plan",
id: "kane-ai-test-plan"
type: "category",
collapsed: true,
label: "Features",
items: [
"kane-ai-javascript-execution",
"kane-ai-geolocation-tunnel-proxy",
"kane-ai-scroll-in-feature"
],
},
{
type: "category",
collapsed: true,
label: "Knowledge Base",
items: [
"kane-ai-command-guide",
"kane-ai-javascript-execution",
"kane-ai-geolocation-tunnel-proxy",
"kane-ai-scroll-in-feature"
"kane-ai-web-test-writing-guidelines"
],
},
{
Expand Down
Loading