Copilots
Last updated
Last updated
Karini AI's Copilots are the innovative end-user applications or chat interfaces that utilize the pre-built recipes as the underlying engines for conversations with end users. You can design copilots that enforce your organizations communications guideline, represent your brand and record essential feedbacks from the users.
For details about designing the copilot interface, refer to .
Key capabilities of Karini AI's copilots:
Users can access Copilots from within Karini AI's platform for which they must have Copilots user, Administrator or Superuser assigned to them. You can also incorporate the copilot within your own domain url and allow your domain users access the copilot interface.
Copilot enables users to pose questions and receive responses, fostering interactive engagement. Karini AI's copilots also supports the streaming experience for almost all SOTA model providers, citations (references), and optional follow-up questions. The feature is vital as it delivers a uniform user experience when enterprises switch between model providers for A/B testing and model upgrades.
Karini AI's Copilot enables you to capture comprehensive feedback from copilot users along with the basic upvote, downvote. You can capture following types of custom feedbacks.
5-stars: Copilot users can rate the content with a 5-star rating.
option: You can configure options to capture feedback on Copilot interactions based your specific requirement. E.g. You may configure the options as "Inaccurate", "Vaguely accurate", "Accurate". These predefined options are made available to the copilot users to provide feedback on Copilot interactions.
text feedback: Copilot users can provide descriptive text feedback.
Correction: Enabling this option will allow the copilot users to provide corrections or improvements to the copilot response.
Karini AI's copilot gives you the flexibility to detect irrelevant or un-related user questions and respond with an appropriate message to engage with users in a positive way and encourage them to ask questions related to the topic.
Users can easily copy both questions and answers, facilitating reference and information sharing.
The Start New Conversation feature allows users to create a new conversation thread, where they can engage in dialogue.This option helps in organizing multiple interactions and keeping them separate for easier tracking and management.
It has following features:
Edit Thread Name: Users can modify the name of the thread for better organization and easier identification.
Delete Thread: An option is available to delete any conversation thread if necessary.
Conversation List: All conversation threads are displayed in the left panel for easy access.
Search Functionality: A search bar at the top allows users to quickly locate a specific thread.
The Smart Search toggle allows users to activate or deactivate the smart search capability within the platform.
When enabled, the system leverages a Dynamic Filtering prompt to construct queries, ensuring that search results are more relevant and contextually appropriate. This enhances the precision of search outcomes, delivering more accurate and customized responses. Additionally, when Smart Search is active, the Metadata Filtering component is also utilized, further improving the efficiency of data retrieval and filtering in the tracing process.
When disabled, the system does not employ dynamic filtering, and the search functionality reverts to a standard search method. As a result, search results may be less contextually relevant, with no advanced filtering applied to refine the data.
There is an icon indicating the option to attach files or documents. This feature allows users to upload relevant files to be included in the conversation or query. Attachments can help provide additional context, such as documents, images, or other data relevant to the user’s request. This function enables the system to process the attached files alongside the user input for more informed responses.
Tracing Feature: Monitoring System Interactions
The Tracing Details feature allows users to track the performance and execution of various components within the system. This function is crucial for monitoring how different tools and processes are utilized in response to a user query, providing transparency and insights into the operational efficiency of the agent.
Prompt Lens Feature: Analyzing Agent Responses
The Prompt Lens feature allows users to view the detailed underlying prompt that guides the agent's responses. It provides transparency into how the system is processing and generating answers based on the user input. This feature is valuable for understanding the reasoning behind the agent's output, including any data retrieval methods, analysis steps, and logical inferences made during the response generation process.
The Audio Feature in copilot facilitates user interaction through both voice input and voice output. Users can verbally submit queries or commands, which are processed by the system to generate text-based responses. Additionally, the system can provide audio responses, creating a more dynamic and accessible mode of communication. This dual functionality enhances the user experience by enabling hands-free interaction and offering flexibility in response delivery, making it particularly beneficial in scenarios where typing is not feasible or for users with accessibility requirements.
You can access the entire chat history of a copilot which is useful for auditing, cost and usage monitoring and performance improvement. You can also derive trends and usage patterns based on the copilot history.
In essence, Copilot represents a powerful platform for interactive engagement, enriched by features such as suggested follow-ups questions, feedback mechanisms, and correction capabilities, ultimately fostering continuous learning and refinement.
<<Copilot Video>>>
This option redirects you to the Export section associated with the Copilot, where you can make necessary edits to the formatting, layout, or any other aspects related to export. You must save the export form in order to make the changes reflected in the copilot for the new sessions.
Request Id: A unique identifier for each request or interaction.
User name: User name of the person interacting with the copilot.
API Session: Session id of the copilot.
Recipe name: Name of the recipe associated with the copilot.
Recipe version: Version of the recipe utilized by the copilot.
Chatbot name: Copilot name.
Status: Status of the responses (e.g. success, aborted, unsafe, greeting).
Question: Query posed by user.
Audio Input: Indicates if audio input was provided.
Answer: Response provided by the copilot.
Error : Any error that occurred during the processing of the request in copilot, such as unexpected failures.
Files: Files uploaded by the user in the copilot interaction, which may be processed or referenced by the system.
Metadata: Additional contextual data related to the request in copilot, such as session details or user context.
Response Type: Type of response (e.g. copilot)
Thread: The conversation thread associated with the request.
Feedback: Feedback provided by the user.
Created: Timestamp when the request was created.
Updated: Timestamp when the request was last updated.
Tokens: Number of tokens utilized in generating the response.
Updated By: User name of person who updated the request.
Faithfulness: Accuracy of the response.
Answer Relevancy: Relevance of the answer to the query.
Audio Response: Indicates if the response was audio-based.
Origin Type: Source of the request (user/system).
Bot Name: The name of the chatbot handling the request.
User Name: The user who made the request.[In external chatbot]
Tenant Id: Unique identifier for the tenant.
Violation Report: Any violations encountered during the interaction.
For each record in the copilot history table, you can view traces to get insights into the detailed step-by-step information about the request processing and response generation. Trace has two sections as Prompt and Attributes.
Prompt: You can view the traces of each operation executed during the processing . It includes the following:
Input
Output
Attributes: These include various parameters and metrics associated with each request. Some of the attributes include:
Input Tokens
Completion tokens
Model parameters such as temperature, max tokens etc.
Copilot history hold valuable information about the user interactions with your copilot, such as the sessions, users, questions, answers, feedback, prompt etc. You can select the record and export this information to use in further downstream processing or auditing, or even to fine-tune the model if required.
You can enable in the recipe to prevent harmful or toxic content from being accepted or generated in the copilot. You have the flexibilty to respond to such content according to your organizations content safety messaging policy.
To upload files within the chatbot, the Global Embedding Model must be selected on the page.
On the copilots list page, you can utilize various the Actions button to carry out the following set of actions. Only Administrator and Superuser can view and perform these actions.
This option redirects you to the underlying Recipe of the Copilot, where you can make necessary adjustments to the recipe pipeline. You must publish the recipe in order for any recipe changes to be reflected in the copilot. You can also create multiple (and hence multiple Copilots) from the same recipe as your use case demands.
This option redirects you to the Copilot History page which includes comprehensive about the copilot activity and a table containing detailed information about the copilot user interactions.