# Step 2: Creating Agents

RAG agents are designed to enhance the quality of generated responses by retrieving relevant information from a knowledge base before generating an answer. They are particularly useful for scenarios where responses require specific, accurate information.

Perform the following steps to create RAG Agents:
Step 2.1: Create RAG agent
Step 2.2: Select RAG Prompt Template
Step 2.3: Select Model and Set Model Configurations
Step 2.4: Provide System Instructions, Knowledge Base, and Examples
Step 2.5: Run the model & Test the RAG agent
Step 2.6: Publish the RAG agent

# Step 2.1: Create RAG agent

1. Head to the Expert Agent Studio module and click Build
2. In the pop up window that appears, Select AI Agent
3. Enter the name and description of the agent. Example, Customer360_Actions
4. In Type, choose Conversational Agent and click Create, the creation page appears

# Step 2.2: Select RAG Prompt Template

5. In the prompt template dropdown, choose RAG template

# Step 2.3: Select Model and Set Model Configurations

6. Select the language model based on your requirement. Example, Azure OpenAI GPT-4o 4k model

# Step 2.4: Provide the System Instructions, Knowledge Base, and Examples

7. System Instructions: Craft a prompt that guides the agent in generating content

   For example,
   System Instruction:
   Answer the question based only on the following context: You are an expert agent that can analyze pending actions to be taken by the personal banking manager for the client from various documents. Identify all the pending actions to be taken by the bank for the particular client. Provide the answers in a numbered list

8. Add Knowledge Base: Click Add and select the created Knowledge Base. For example: Customer360. This provides the necessary information for the agent to extract relevant and accurate data

# Step 2.5: Run the model & Test the RAG agent

9. In the Test and Debug section, enter the appropriate prompt. For example , Identify pending actions to be taken for the client
10. Click the send icon or press Enter key to run the prompt
11. Review the generated response to ensure it adequately addresses or clarifies your query

# Step 2.6: Publish the RAG agent

12. Click Publish
13. In the Asset Details page that appears, enter the Welcome Message as “Welcome to AI Chat!” Or leave it blank
14. Click Publish and the status of the agent is changed to published once the agent gets published

Create other agents in the similar way and proceed further to create the teams of Agents

RAG Agents created for Customer 360 (example):
Using Customer360 and Customer360_CFR knowledge bases the following RAG agents are created:

• Customer360_Actions RAG Agent: Retrieves pending actions to be taken by the personal banking manager from the customer360 knowledge base
• Customer360_Opportunities RAG Agent: Extracts cross-sell and upsell opportunities for the client from the customer360 knowledge base
• Customer360_Contentment RAG Agent: Analyzes client satisfaction and sentiment levels using the customer360 knowledge base
• Customer360_Risk RAG Agent: Identifies potential risks of the client leaving the bank based on insights from the customer360 knowledge base
• Customer360_CFRD RAG Agent: Extracts a complete set of insights (risks, opportunities, contentment, and actions) specifically from the Client Financial Review Document present in the Customer360_CFR Knowledge base, outputting results in a structured JSON format.