Build Agent Pipelines in AgentCreator

These steps summarize the process for creating an Agent pipeline in Designer. The pipeline follows the agent architecture: Prompt Generator Snaps handle prompt construction and context, Function Generator Snaps define the available tools, and the Agent Snap drives the LLM reasoning and tool-calling loop.

Tip: The following tips are for building pipelines in Designer:
  1. For easy debugging, we recommend that when you start, you already have a few tool pipelines created.
  2. If you plan to have multiple unconnected pipelines in one canvas, use the Disable Snap setting to turn off pipeline segments from validating and executing.
  3. Use a JSON Generator Snap in your tool pipelines to mock data input for testing purposes. It can be disconnected and disabled later.

Activities outside of SnapLogic would be:

  • Creating an interface for your end users to interact with the agent.
  • Using a 3rd-party monitoring tool to assess the quality of responses and LLM costs.
  • Plan your agent pipeline design.
    1. Objective - Define a specific goal for your agent is crucial as a first step.
    2. Preparation - Collect data and prepare a real-world context for the types of end-user questions the agent is designed to answer.
    3. Tools - Enumerate the tools required for the agent to respond best to the prompt and determine the layers of pipelines that inform the hierarchy of agents. Refer to Create tool pipelines.
    4. Data sources - Identify data sources for the agent. This applies to RAG pipelines especially.

  • Make sure your LLM Snap accounts are configured. Refer to the following for LLM configuration details:

  • Set up your Snaplex to validate and run your pipelines.
  1. Go to Designer and create the following Agent pipeline:

    From the Snap Catalog, add the following Snaps to the canvas in order:

    1. JSON Generator Snap

      Use the JSON editor for the initial user prompt. This creates the JSON document that is sent through the pipeline with the prompt input. During development, this simulates user input before a real interface is connected.

    2. Prompt Generator Snap

      Each Prompt Generator Snap carries a distinct prompt: the first defines the agent's role via the system prompt, the second carries the user's request.

      1. Click Prompt Composer and enter the prompt.
      2. Select the System Prompt checkbox and define the role.
      3. Add a second Prompt Generator Snap and in the Prompt Composer, enter the user prompt.
    3. Add a Function Generator for each tool definition.

      Function Generator Snaps produce the tool definitions that tell the LLM which tools are available and what parameters are required to call them. Select the Function Generator that matches your LLM vendor:

      • Amazon Bedrock Function Generator: You can use this Snap to generate a tool definition for the Amazon Bedrock LLM endpoint.
      • Azure OpenAI Function Generator: You can use this Snap to generate a tool definition for the Azure OpenAI LLM endpoint.
      • Google GenAI Function Generator: You can use this Snap to generate a tool definition for the Google Gemini LLM endpoint.
      • OpenAI Function Generator: You can use this Snap to generate a tool definition for the OpenAI LLM endpoint.
      • OpenAPI Function Generator: You can use this Snap to generate tool definitions from an OpenAPI specification.
      • APIM Function Generator: You can use this Snap to generate tool definitions from an APIM service.
      • Function Generator: You can use this Snap to generate tool definitions for any Agent Snap. It informs the model about the tools that the user can call, including their names, descriptions, and required input parameters. This simplifies the process of defining custom tools compared to manual JSON construction.
      • Multi Pipeline Function Generator: You can use this Snap to transform pipeline properties and parameters (such as pipeline name, purpose, and OpenAPI parameters) into function definitions.
      • MCP Function Generator: You can use this Snap to generate a list of tool definitions from the tools available on an MCP server, with the additional ability to add "list resource" and "read resource" to the function definitions list.
    4. Add the Agent Snap per LLM vendor you plan to use.
  2. Configure the Function Generator Snaps.
    1. Specify the name, description, and any parameters for your tool definition.
    2. In the Tool Path field, select the tool pipeline from the dropdown

      This links the tool definition to the pipeline the Agent Snap will invoke when the LLM calls that tool.

      Tip: Tagging your pipelines as tools filters the dropdown so that only tool pipelines display.
    3. For APIM and OpenAPI Function Generator Snaps. In the Account Path field, select the LLM Snap account.
    4. Save and close the Snap.
  3. Configure the Agent Snap.
    1. On the Accounts tab, select the account.
    2. On the Settings tab, specify the basic configuration.
    3. For advanced settings, configure the following sections of the Agent Snap form:

      These settings control how the Agent Snap executes its iterative reasoning loop and interacts with the LLM and tools.

      1. Agent execution configuration: Defines how the Agent iterates on the prompt and responses from the tools.
      2. Model parameters: Specifies the behavior of the model.
      3. Advanced tool configuration: Defines the tool response.
      4. Advanced prompt configurations: Provides options for different prompt modes.
      5. Advanced response configurations: Defines the LLM response.
    4. Save and close the Agent Snap.
  4. Click to open Pipeline Properties dialog:
    Note: Adding an Agent Snap to the pipeline automatically tags it as an Agent. No manual tagging is required.
    1. Enter the name of the Agent.
    2. Add additional pipeline parameters if needed.
  5. Verify that your Agent pipeline runs successfully.
    1. Click Validate icon to validate the pipeline.
    2. When validation is completed, open the Agent Snap, and click Visualize agent flow.

      The AgentVisualizer page opens with a graph and log of the input and the Agent response.

      Example of an Agent Visualization

  6. Deploy your agent to production. You can view Pipeline executions in Monitor.

    These activities include:

    • Create a Triggered Task or Ultra Taskfor the pipeline.
      Note: Once the pipeline is in production, you should disable or remove the JSON Generator Snap. The open input for the data source would trigger the pipeline.
    • Move the Task, pipelines, and associated assets (such as an accounts file or expression library) to a production Environment (Org).
    • Assign the pipeline a Snaplex in your production environment.
    • View execution statistics in Monitor.

The following table provides Agent Snap patterns based on LLM vendor.

LLM Vendor

Pattern

Amazon Bedrock AgentCreator Agent - Amazon Bedrock - Personal assistant agent
Azure OpenAI AgentCreator Agent - Azure OpenAI - Personal assistant agent
Google Gemini AgentCreator Agent - Google Gemini - Personal assistant agent
OpenAI AgentCreator Agent - OpenAI - Personal assistant agent