Using Agent

Applicable Scenarios

1. Internal Enterprise Knowledge Q&A

   • Employees can ask questions about HR policies, financial processes, IT support, etc. through the chat window, and the system will automatically retrieve answers from the knowledge base.
   • For example: The HR Assistant can answer questions like "How long is the probation period?" or "How to reimburse expenses?", while the Finance Assistant can handle "Invoice precautions", "Travel reimbursement process", "Q1 sales performance", etc.

2. Intelligent Document Parsing and Q&A

   • Supports uploading PDF documents and enables intelligent Q&A based on document content.
   • Allows switching between multiple documents for comparison and inquiry, suitable for contract review, technical document analysis, training material Q&A, etc.

3. Multi-Document Knowledge Base Q&A

   • Administrators can upload multiple policy documents, SOPs, FAQs to build a knowledge base.
   • When users ask questions, the system will accurately match and provide answers from the knowledge base, suitable for standardized Q&A in HR, Finance, QA, CSC, and other departments.

4. Internet Search and External Information Acquisition

   • Public domain assistants support internet search, suitable for obtaining the latest news, industry trends, technical updates, and other content not trained by GPT.

How to Use Agent?

Start a Conversation

Natural language conversation is the main way to interact with the Agent, just like chatting with a person. Users can ask the Agent questions or request it to perform tasks using natural language.

For example:

• Ask the Agent to perform an internet search: "Please help me search for chip industry companies in Shanghai, Guangzhou, and Beijing via the internet."
• Ask the Agent to assist with drawing: "Please generate two origami-style illustrations for my PPT cover and end page, one showing sunlight through a window, and the other showing a camel walking in the desert."

Steps:

1. Log in to the SERVICEME platform
2. Go to the AI Astudio page
3. Select the appropriate Agent in the Agent panel, such as Copilot (default Agent name)
4. Ask your question and wait for the output

Additional Notes:

• Voice Input: You can input via voice
• Image Attachment: Paste or select an image to converse, e.g., "Please interpret the meaning of this image"
• New Conversation: Start a new conversation topic, which will not be affected by the current conversation context

View Conversation History

Each time a new conversation is initiated, the system automatically generates a history record, making it easy for users to review previous exchanges at any time.

• View Conversation: Click the title of a historical conversation to revisit the dialogue, helping you quickly find past communication content.
• Quick Search: Enter keywords from the title to quickly locate relevant historical conversations.
• Delete/Rename: Use the edit button on the right side of the historical conversation to delete or rename it.

How to Narrow the Knowledge Scope for Q&A?

When the Agent is associated with too much knowledge, there may be contradictions between different pieces of information. To ensure accuracy, you can optimize results by limiting the scope of knowledge for Q&A. Here are two main filtering modes:

• Knowledge Workspace
  • This mode allows users to restrict the Q&A scope to one or more specific knowledge spaces.
  • It also allows limiting the Q&A scope to a particular file.

• Tag
  • Users can select the Q&A scope using one or more specific tags.

Operations Based on Replies

Rate Replies

For replies generated by the Agent, users can rate them by upvoting or downvoting.

• If satisfied with the reply, hover the mouse over the reply and click to upvote the content.
• If not satisfied with the reply, hover the mouse over the reply and click to provide negative feedback.

• Provide Detailed Feedback

tip

Detailed feedback requires the Agent to enable "Chat Feedback".

Copy Reply

Copy the reply content, including its formatting and images (the target must support HTML format, such as Word).

Add Reply to QnA

If the user considers the reply to be of high quality, the Q&A can be saved to QnA. When other users ask the same question later, this QnA will be prioritized for replies, helping to improve response quality.

Instructions:

• File Space: Select the target space to store the QnA. Users need access permission to the corresponding space to retrieve QnA;
• Question: The QnA question, which can be modified based on the original inquiry;
• Answer: The QnA answer, which can be modified based on the original reply.

tip

• "Answer" supports rich text/HTML tags. It is recommended to limit the total to within 2000 characters, which will help AI responses.

View Reference Sources

If you want to know which specific fragments or documents the answer references, you can view them via the links in the reply.

Question Guidance and Follow-up

1. Intelligent Question Recommendation and Auto-completion

   • When users enter a question in the chat box, the system uses intelligent algorithms to automatically generate related questions that may interest the user for reference.
   • If the user's question is incomplete, the system will automatically complete it, ensuring a smoother and more efficient interaction.

2. Follow-up Function

   • After Q&A, users can ask further questions based on the assistant's reply, files, or tags.
   • The specific method for follow-up is:
     • Click the file or tag after the assistant's reply,
     • Click "Ask Again" below the reply, and the assistant will further narrow the scope based on the file and tag for a more targeted answer.

💡 Tip: Before using this feature, you need to enable question guidance and follow-up options in the agent configuration.

Private Domain Knowledge Q&A

When using the assistant, if you want to perform Q&A based on a private domain knowledge base, you can configure it as follows:

• Go to the assistant configuration page and turn off the "Allow File Upload" button in Knowledge Source Configuration.
• Click the "+" button on the right side of the knowledge source to add private domain knowledge base content to the assistant.
• Click the settings button on the right side of the knowledge source and enable the "Enforce Private Domain File Q&A" option.
• After configuration, click the "Save Configuration" button in the upper right corner to successfully create a private domain Q&A assistant.
• After successful configuration, you can perform appropriate tests to ensure the private domain Q&A function works properly.

💡 Tip: After the assistant enables enforced private domain Q&A, internet search skills will be disabled by default, and internet search will no longer be available.

Single Document Q&A

When using the assistant, if you want to perform Q&A on a single document, you can select a single document in the knowledge scope after configuring the knowledge source for the assistant.

• Click "Knowledge Scope", select a single document, and click "Confirm".
• After selecting a single document, you can perform Q&A targeting that document.

In addition to selecting a single document in the knowledge scope for Q&A, you can also use AI summary for document Q&A.

• Find and preview the document in the knowledge base;
• On the preview page, click "Chat" at the top to open the assistant named "File Copilot" for document Q&A.

Multi-Document Q&A

Multi-document Q&A is similar to single document Q&A. After configuring the knowledge source for the assistant, select multiple documents in the knowledge scope.

• Click "Knowledge Scope", select multiple documents, and click "Confirm";
• After selecting multiple documents, you can perform Q&A targeting these files.

tip

• When selecting files in the knowledge scope, you can also select the entire knowledge base for Q&A, but only if the knowledge base is selected in the assistant configuration's knowledge source settings.
• Additionally, the knowledge scope does not support selecting folders; only files or knowledge bases can be selected.