How to set up and customize your app?
Last updated
Last updated
Below is a step-by-step guide on how to set up and customize your app for optimal user interaction.
Once created, you'll find a link to your app on the overview page. Share this link with others to grant access to your knowledge base outside of the platform.
Users can integrate a conversational widget into their website by pasting the provided code into the head section. This widget will appear at the bottom right corner of the page, allowing users to engage with the bot.
Toggle the ‘Collect User Info’ option to prompt users to provide information when interacting with the bot. Users can specify the type of information to collect and provide a title for the user information form. After toggling, click ‘Save’ to apply the changes.
Click on the ‘Edit your appearance’ button to access the appearance tab, where you can customize the look and feel of the conversational widget. Make desired changes and click ‘Save and update preview’ to apply the modifications.
Navigate to the ‘Configure Your Bot’ tab to access extensive customization options that enhance the functionality and user experience of your application.
Select your orchestration method: You can choose between using a knowledge base for information-driven responses or employing predefined Flows to guide interactions.
Adding resources For knowledge base: Include relevant knowledge bases your bot will refer to for information. Additionally, define the schema to structure the knowledge base for optimal retrieval and presentation of information. For Flow: If opting for Flows, integrate the necessary predefined Flows that your bot will follow during interactions to ensure smooth and guided user experiences.
Provide specific instructions or guidelines that the bot should follow during user interactions.
Click on ‘View Settings’ to display the current configuration of your app/bot. This will show all the parameters and settings currently in place.
Auto configuration
To automatically configure your app, click the ‘Start’ button. The system will configure the best settings for your app, which may take 10-15 minutes. You can monitor the configuration accuracy under ‘Bot Performance.’
Manual configuration
You can also manually configure your app by adjusting parameters such as model selection, temperature, context length, etc. After making the necessary adjustments, click ‘Update Settings’ to apply the changes. If you wish to discard changes and return to the original settings, click ‘Default Settings.’
After completing all the necessary adjustments and configurations, click the ‘Save’ button to apply and save your settings.
The user can now test their bot's performance using sample questions, known as ‘Golden Questions,’ to evaluate accuracy. After generating the test report, users can view detailed metrics, including the accuracy for each question, the ZBrain answer, and the correct answer provided by the user. They can access the full context used to generate answers, adjust accuracy settings as needed, revert to previous versions if necessary, and delete any versions they have created. This comprehensive testing process ensures the bot meets the desired performance standards.
Golden questions are sample questions used to test the bot's performance. Follow these steps to add golden questions:
Go to the ‘Test Questions’ tab on your dashboard.
Enter your test questions and the corresponding correct answers based on your knowledge base.
Click the ‘Save’ button to save the test questions and answers.
After saving the golden questions, click ‘Test Bot Performance’ to check the bot's performance report.
After initiating the test, you will be redirected to the ‘Bot Performance’ tab. Here, you can review the performance report generated from the test. Detailed report includes:
Accuracy of each question: See the accuracy score for each individual question, including the ZBrain answer and the correct answer provided by you.
Default settings in use: View the current settings used during the test.
Current version: Identify the version of the bot configuration used for the test.
View the entire answer: Click the '+' icon in each row to view the complete answer provided by the bot.
If needed, you can adjust the accuracy by clicking the ‘Edit’ button within the accuracy column for each test question and answer.
If you want to delete a specific version, use the ‘Delete this Version’ button to remove it from the list.
The ‘Query History’ tab provides valuable insights into the interactions users have had with your bot. Here's how you can leverage this feature:
Navigate to the ‘Query History’ tab on your dashboard.
On the ‘Query History’ page, you will find the following information:
Session IDs: Each interaction session with the bot is assigned a unique session ID, allowing for easy tracking and reference.
User information: Users' names and email addresses associated with each session are displayed, providing context for the queries.
Prompt count: The number of prompts or interactions within each session is recorded, giving an indication of user engagement and interaction depth.
Session time: The duration of each session is logged, helping to analyze the duration of user engagements and overall bot usage patterns.
By reviewing the query history, you can gain insights into user behavior, identify trends, and make informed decisions to optimize the bot performance and user experience.
At the top of the Reports page, you will find the following metrics and detailed session data including:
Total sessions: The total number of sessions.
Average response time: The average time taken to respond to queries.
Satisfaction score: The average user satisfaction score.
Total token used: The total number of tokens used.
Use the search bar to find specific sessions by entering the session ID, user name, or date.
Alternatively, you can click the ‘User' drop-down menu and select 'All’ to view all users or choose a specific user.
The Reports page lists detailed information about each session, including:
Session ID: A unique identifier for each session.
User name: The name of the user who initiated the session.
Session start date and end date: The date and time when the session started and ended.
Session time: The total duration of the session.
Number of queries: The total number of queries asked during the session.
Total response time: The cumulative time taken to respond to all queries in the session.
Satisfaction score: The user’s satisfaction rating for the session.
Tokens used: The number of tokens consumed during the session.
Cost: The cost associated with the session based on token usage.
You can sort the session data based on any of the listed columns to organize the information as needed.
To export the report, follow these steps:
Click on the ‘Export’ button located at the top right of the Reports page.
Select the specific data fields you want to include in the export.
Click on the ‘Export’ button again to generate a CSV file.
The CSV file will be available in your downloads folder.
Reports are useful for monitoring and analyzing user sessions, providing insights into usage patterns and performance metrics. Use search, sort, and export functionalities to manage and review session data effectively.
