This use case demonstrates how to provide a simple question to the specified Anthropic model. The simple prompt focuses on clarity and conciseness, avoiding complex phrasing or unnecessary details that can potentially confuse the model.

1. Configure a REST Adapter trigger connection.
2. Configure an Anthropic Adapter invoke connection. See Create an Anthropic Adapter Connection.
3. Create an application integration.
4. Drag the REST Adapter trigger connection into the integration canvas for configuration. For this example, the REST Adapter is configured as follows:
   • A REST Service URL is defined (for this example, /anthropicsimple).
   • A Method of POST is selected.
   • A Request Media Type of JSON is selected and the following sample JSON structure is specified:

     { "messages" : [ { "role" : "user", "content" : "Hello there." }, { "role" :
           "assistant", "content" : "Hi, I'm Claude. How can I help you?" }, { "role" : "user",
           "content" : "Can you explain LLMs in plain English?" } ] }

   • A Response Media Type of JSON is selected and the following sample JSON structure is specified:

     { "id" : "msg_01QYBJH7FVfL9kGt9a8Adgyj", "type" : "message", "role" :
           "assistant", "model" : "claude-opus-4-20250514", "content" : [ { "type" : "text",
           "text" : "I'll help you get the current weather and time in New York." }, { "type" :
           "tool_use", "id" : "toolu_01XUJFZr22Cy65yQGjC9Abc8", "name" : "get_weather",
           "input" : "input value" }, { "type" : "tool_use", "id" :
           "toolu_013sXxnS8VD7Db2oFo1Cxf4k", "name" : "get_time", "input" : "arguments" } ],
           "stop_reason" : "tool_use", "stop_sequence" : "stop", "usage" : { "input_tokens" :
           532, "cache_creation_input_tokens" : 0, "cache_read_input_tokens" : 0, "output_tokens" :
           111, "service_tier" : "standard" } }

5. Drag the Anthropic Adapter invoke connection into the integration canvas and configure it as follows.
   1. From the Anthropic LLM Models list, select the model to use (for this example, Claude Opus 4 is selected).
   2. From the Request Type list, select Simple Prompt.
6. Open the request mapper automatically created when the Anthropic Adapter invoke connection was added to the integration. The mapper that was automatically created with the REST Adapter trigger connection is not edited and remains empty in this use case.
7. In the request mapper, map the source Messages elements to the target Messages elements.
   
   

   

   
   
8. Add a response mapper.
9. In the response mapper, expand the source Response Wrapper element and target Response Wrapper element and perform the following source-to-target mappings..
   
   

   

   
   
10. Specify a business identifier and activate the integration. For this example, the Debug tracing level is selected.

    The completed integration looks as follows:

    
    
    

11. From the Actions menu, select Run.
    The Configure and run page appears.
12. In the Body field of the Request section, enter the following content, then click Run.
    • role: The roles for the user that is commenting/questioning and the assistant that is responding.
    • content: The message contents.

    {
      "messages": [{
        "role": "user",
        "content": "Hello there."
      }, {
        "role": "assistant",
        "content": "Hi, I'm Claude. How can I help you?"
      }, {
        "role": "user",
        "content": "Can you explain LLMs in plain English?"
      }]
    }

    The Body field of the Response section returns the following output.

    {
      "id" : "msg_013HeB3TaTKmLPSimSbctotz",
      "type" : "message",
      "role" : "assistant",
      "model" : "claude-opus-4-20250514",
      "content" : [ {
        "type" : "text",
        "text" : "Sure! LLMs (Large Language Models) are computer programs that have learned 
    to understand and generate human-like text by studying massive amounts of writing from the 
    internet, books, and other sources.\n\nThink of them like very advanced autocomplete 
    systems. Just as your phone can predict the next word you might type, LLMs can predict 
    and generate entire sentences, paragraphs, or even essays that make sense.\n\nHere's how 
    they work in simple terms:\n\n1. **Training**: They read billions of pages of text and 
    learn patterns - like how words typically go together, grammar rules, and facts about the 
    world\n\n2. **Size**: \"Large\" means they have billions of connections (parameters) that 
    help them remember and use what they've learned\n\n3. **Capabilities**: They can answer 
    questions, write stories, translate languages, summarize text, and have conversations - 
    basically anything involving understanding or creating text\n\n4. **Limitations**: They 
    don't truly \"understand\" like humans do - they're pattern-matching machines. They can 
    make mistakes, generate false information, or produce biased content based on their 
    training data\n\nPopular examples include ChatGPT, Claude (that's me!), and Google's Bard. 
    They're useful tools, but it's important to remember they're not human and should be used 
    thoughtfully."
      } ]
    }

13. Expand the activity stream to view the flow of the message sent by the invoke connection to the Anthropic model: