"Hello. This wiki will provide insights into Axero Copilot and best practices for effectively implementing me among your users."

What Is Axero Copilot?

Axero Copilot is an advanced AI-powered chatbot built on the foundation of OpenAI's GPT technology. Axero Copilot is uniquely designed to operate within your organization's intranet, providing a private and secure environment for accessing and interacting with internal content. 

Unlike traditional search engines or knowledge management systems, Axero Copilot goes beyond simply retrieving relevant documents; it comprehensively reads and analyzes content to provide concise, accurate responses to user queries. By utilizing natural language processing, Axero Copilot enables users to engage in conversational interactions, significantly enhancing knowledge discovery and retrieval within the organization.  

Axero Copilot Features & Capabilities

Search Results: Axero Copilot is designed to search for keywords and read unfiltered documentation results to provide answers efficiently. 

Unfiltered documentation search results are derived from the following content types:

• Articles
• Wikis
• Blogs

Excluded content types are:

• Events
• Tasks
• Cases
• Recognition

While Axero Copilot's primary function is to search documentation content effectively, it may also read and understand:

• A subset of user profile data
• Some text page builder pages

Access to Intranet Content: Axero Copilot has exclusive access to your organization's intranet content, ensuring all interactions occur in a secure environment. It can search through a wide array of documents, including articles, presentations, and files, providing users instant access to valuable information. Axero Copilot can also read and display text from supported document files, including PDF, DOCX, PPTX, and XLSX, as well as image-based or scanned PDFs, directly in the chat, presenting relevant text and context in a structured format.

Conversational Interface: Unlike traditional search interfaces, Axero Copilot offers a conversational experience that feels like interacting with a colleague or teammate. Users can ask questions naturally without navigating complex search queries, facilitating smoother knowledge retrieval processes.  

Personalization and Permissions: Axero Copilot operates on a personalized, permissioned basis, ensuring that users access only content relevant to their roles and permissions within the organization. This customized approach enhances data security and confidentiality.

Content Analysis and Relevance Scoring: Axero Copilot uses logic to analyze content and assign relevance scores to retrieved information. This enables it to prioritize and present the most pertinent details to users, streamlining the information retrieval process.

Mentions: Axero Copilot supports @mentions to reference people, spaces, or content and retrieve relevant information directly within the conversation. Typing the @ symbol in the Copilot chat input displays a dropdown list of available results based on user permissions. Only items that the user has permission to view will appear in the list. Selecting an item inserts a formatted reference (example: @Laura Carter) that prompts Copilot to return a profile summary, content details, or related links, depending on what is mentioned. Mentions are enabled by default.

Conversation History: Axero Copilot saves conversations, allowing users to return to previous chats and continue where they left off. In full-screen mode, prior conversations can be viewed and searched for the selected Copilot profile.

Customization Options: Each Axero Copilot installation can be tailored to your organization's specific requirements and branding preferences. Customization options ensure seamless integration with existing systems and workflows, from the interface design to the naming conventions and logo. This includes key UI features that enhance usability and accessibility: 

• Full-Screen Mode: Enhance your interaction with Axero Copilot by switching to full-screen mode. This feature allows for an immersive experience, minimizing distractions and maximizing usability. It’s ideal for focused tasks and in-depth consultations with the Copilot, enabling users to fully engage with the content and tools available.

• Preset Questions: To help users get started, preset question prompts can be added at the start of a chat. These clickable prompts feature intuitive icons and can be auto-submitted to quickly access common queries. They provide a quick entry point for common queries, improving the user experience by guiding users to helpful information.
• Embedded Copilot: Axero Copilot can be embedded directly within a page for a more visually integrated experience. This allows it to blend seamlessly into the existing interface, keeping it accessible without disrupting the overall layout and design.

How Axero Copilot Works

When a user asks a question, Axero Copilot locates relevant information and responds with a concise text summary. Below the line, Axero Copilot primarily targets content that provides insights into user query responses. It includes relevance scores and references to similar topics, all tailored based on user permissions to ensure access to authorized content only.

• Search and Retrieval: When a user poses a question, Axero Copilot conducts a comprehensive search across the entire intranet to find relevant information.
• Content Analysis: Axero Copilot reads and analyzes retrieved documents, identifying key details and extracting relevant information.
• Conversational Interaction: Users engage with Axero Copilot through conversational interactions, asking questions and receiving concise responses based on the analyzed content.
• Relevance Scoring: Axero Copilot assigns relevance scores to retrieved information, prioritizing the most important details for user consumption. 
• Feedback Option: After receiving an answer, users can provide feedback. If the response wasn't helpful, they can specify the reason and provide additional details before submitting the feedback.

Are Customizations Possible?

Axero Copilot can be customized through the Axero Copilot Manager, which provides several options to tailor the experience to your organization:

Appearance and Branding
Update the Axero Copilot name, avatar, launcher icon, and loading animation to match your intranet’s branding.

Suggested Questions
Add, reorder, and style preset questions to guide users toward common tasks and help them get started quickly.

Knowledge Access Controls
Control what Axero Copilot can search by limiting its access to specific spaces, content types, tags, or a dedicated Bot User for consistent, permission-aware results. 

Multiple Profiles (if enabled)
Create separate Copilot profiles for different audiences or use cases, such as HR, IT support, leadership, multilingual sites, or regional teams.

Axero Copilot Analytics

Analytics provides administrators with invaluable insights into Axero Copilot user interactions, enabling them to optimize performance and enhance user satisfaction. With sorting, filtering, customizable timeframes, and detailed session information, administrators can review activity, analyze feedback, and understand user behavior to optimize Copilot's performance and enhance user satisfaction.

Learn more about Axero Copilot Analytics here

Axero Copilot Best Practices

Here are some best practices to help guide your organization in rolling out Axero Copilot among your users. These recommendations will optimize user adoption and enhance the overall effectiveness of the Axero Copilot Implementation process.

Content Size Optimization

Axero Copilot is masterful at scanning large amounts of content, but it also limits how much it can read before synthesizing a response. If your Axero Copilot is having difficulty digesting large files and documents, connect with your implementation specialist to identify the best strategy to help your users get the responses they need. We may adjust prompts to focus the AI's attention, upgrade GPT models for deeper document comprehension, or employ other strategies to make content more digestible, such as splitting long PDFs into multiple parts. 

Formulating Effective Queries

We encourage users to ask specific questions in natural language. Instead of vague inquiries, we encourage users to be precise and provide context where necessary. Include relevant keywords or phrases to help Axero Copilot better understand your query and provide accurate responses.

• Here is an example of formulating an effective query for Axero Copilot:
  • Ineffective Query: "Budget report"
    • The ineffective query, "budget report," is quite general and could encompass many references or information.
  • Effective Query: "Can you provide the budget report for Q1 2024 for the Finance department?"
    • The effective query specifies the period (Q3 2023) and the department (Finance), providing clear parameters for Axero Copilot to search within.

Narrowing/Focusing Responses

When users must follow up on initial responses to gain more focused or detailed information, they can do this by asking clarifying questions or providing additional context to steer the conversation in the desired direction.

• Here's an example of narrowing or focusing a response after receiving an initial answer from Axero Copilot:
  • Initial Query
    • User: "How do I set up a virtual meeting using our company's video conferencing software?"
  • Initial Response
    • Axero Copilot: "To set up a virtual meeting using our company's video conferencing software, follow these steps: 

1. 1. 1. 1. Log in to the software using your company credentials.
         2. Navigate to the 'Schedule Meeting' option.
         3. Enter the meeting details, including the date, time, and participants.
         4. Choose the desired settings, such as audio and video preferences.
         5. Click 'Schedule' to confirm the meeting."

• • Narrowing/Focusing Response: 
    • User: "Thanks for the steps. Could you also clarify how to invite external participants to the meeting?"
      • By asking a follow-up question to clarify a specific aspect of the initial response, the user can receive targeted information that directly addresses their needs. In this example, the user seeks additional guidance on inviting external participants to the virtual meeting, allowing Axero Copilot to provide further instructions or tips tailored to this particular requirement. 

Understanding Responses

When discussing Axero Copilot with your users, emphasize the importance of paying attention to the relevance score assigned to each response, as higher scores signify greater alignment with the query. 

• Here's an example of the relevance score (r:90) from Axero Copilot:

Providing Feedback and Types of Useful Feedback

We encourage users to regularly provide feedback after interactions with Axero Copilot, as this can offer insights to progressively enhance performance and accuracy. Instruct your users to specify the reason for their feedback, whether it pertains to identifying inaccuracies, suggesting improvements, or expressing satisfaction with the provided responses.

Note: Axero Copilot can be configured to require feedback after each interaction, ensuring valuable input is consistently collected for ongoing improvements.

• Here's an example of Axero Copilot feedback interface: 
  • Teach users to distinguish between feedback on the content of the response (accuracy, relevance) and feedback on the functionality or user experience of Axero Copilot (ease of use, speed). 

• Here's an example of good and bad feedback:
  • Helpful Feedback: "The response provided by Axero Copilot was accurate and helped me quickly find the information I needed. It precisely addressed my query and saved me a lot of time."
    • Why it's helpful: This feedback highlights the response's accuracy, specifies how it helped, and acknowledges the time-saving aspect of using Axero Copilot.
  • Unhelpful Feedback: "Axero Copilot's response was inaccurate. It didn't address the main point I was asking about. This tool is useless."
    • Why it's unhelpful: This feedback only states that the response was inaccurate without specifying what caused the issue or providing any details about the query. It also uses a strong adjective ("useless") without offering suggestions for improvement.

What Your Axero Copilot Can't Do

Understanding what Axero Copilot can't do is essential to managing expectations and maximizing utility. While Axero Copilot is a capable assistant, it's important to acknowledge its limitations—such as making your coffee! Axero Copilot may not always provide contextually refined responses. Some scenarios where it can't do its magic include:

Lack of Documented Procedures

• User Query: "How can I troubleshoot an issue with my Lenovo ThinkPad P14s workstation?"
• If the troubleshooting procedures for the technical issue are not adequately documented within your Axero site, Axero Copilot will not be able to provide detailed or comprehensive guidance. Incomplete or outdated documentation on your Axero site will limit Axero Copilot's ability to retrieve relevant troubleshooting steps, resulting in unsatisfactory answers for users seeking assistance with technical issues. 

Insufficient Coverage of Specialized Topics

• User Query: "What are the best practices for communicating with the IT department?" 
• If your Axero site lacks comprehensive coverage of specialized topics such as communicating with IT, Axero Copilot will struggle to provide satisfactory answers to best-practice queries. Limited or outdated content on specialized topics on your Axero site can hinder Axero Copilot's ability to retrieve relevant information, resulting in less helpful responses for users seeking guidance on specific practices.

Highly Contextual or Personalized Queries

• User Query: "What tasks should I prioritize for my role as a marketing manager in the upcoming quarter?" 
• Axero Copilot will struggle to provide personalized task prioritization recommendations tailored to your users' specific roles and responsibilities within your organization. Such queries require a deeper understanding of your users' individual context and priorities, which Axero Copilot cannot discern solely from your intranet site content. 

Ambiguous or Unclear Queries

• User Query: "Tell me about the latest content."
• The query "latest content" is ambiguous and lacks specificity, making it difficult for Axero Copilot to determine the intended topic. Without additional context or clarification, Axero Copilot will provide generic or broad responses that may not fully address the query. 

Sensitive or Confidential Information Queries

• User Query: "What is my salary?" 
• Axero Copilot will not have access to or be authorized to retrieve sensitive or confidential information, such as salary details. Queries that involve this information may be outside Axero Copilot's capabilities and access permissions, as retrieving it could pose privacy and security risks. 

In these situations, you may need assistance from human experts or consult external resources to obtain satisfactory answers. Understanding these boundaries helps our users use Axero Copilot effectively, recognize its strengths, and know when to seek additional support, even if it's just for a caffeine boost!