AgentCreator Architecture and Pipeline Design
The SnapLogic platform lets you connect to multiple data sources, create prompts, and interact with large language models (LLMs) through a single user interface. In SnapLogic AgentCreator, an agent is a group of SnapLogic pipelines. With AgentCreator, you can design simple, goal-based agents. You can also build multilayered agents that include subagents for more complex tasks.
This article covers the following topics:
- AgentCreator pipeline architecture
- AgentCreator pipeline design considerations
AgentCreator pipelines power agent operations. They can connect to any data source supported by SnapLogic Snaps. You can build the user interface for these agents using your organization’s tools or platforms such as Streamlit. For example, SnapLogic AgentCreator can handle the agent’s back-end APIs, while Streamlit provides the user interface.
For example, in this solution, SnapLogic AgentCreator handles the back-end APIs while Streamlit powers the agent end-user interface.
The Prompt Composer
Agent requests are entered via the Prompt Composer, which is launched from the Prompt Generator Snap. An Agent pipeline is composed of a chaining of Prompt Generator Snaps that achieve a complex prompt. You can use the Prompt Composer to develop and iterate on prompts for your agent.
System prompt
Defining a role for agents and their subagents is an important part of returning output in a format that suits your usecase. You can define the role of the agent by selecting the system prompt in the appropriate Snap for the LLM vendor/model.
The system prompt is for the model to understand the persona it should adopt (displayed in the UI as the field Role). While not required, creating a system prompt makes things easier by creating a set of instructions for the LLM, as opposed to sending a request.
You can leverage the system prompt for the underlying system receiving the prompt input. This enables you to create layers of agents.
Agent Snap
The Agent Snap calls the LLM with the request. You can add an Agent Snap to a driver pipeline, and it will call the required tools. Because the Agent Snap is LLM vendor dependent, the pipeline design might be more restrictive than the conventional agent pipeline design.
LLM Snap Packs contain an Agent Snap:
- Amazon Bedrock Converse API Agent
- Azure OpenAI Chat Completions Agent
- Google Gemini API Agent
- OpenAI Chat Completions Agent
JSON mode
JSON mode is for the model to output in JSON format. JSON format can be leveraged relaying output data from the LLM to other systems.
For agents that rely on LLM thinking and reasoning models, structured outputs can be leveraged for specific formatting input and output requirements.
Tool Pipelines
Tool pipelines are the actual tools the Agent pipeline calls.
For example, an agent assisting with near-term travel planning might retrieve the temperature using a tool from a weather website. As the agent end user, you would enter a prompt into an input field through an application interface.
Operationally, that prompt input is sent as a request to the Agent Snap, which carries out iterations, interacting with the tools. The response is then passed back through the loop, in case more iteration on the request is required.
The following diagram illustrates the request flow in tool pipelines:
The processing is accomplished through four types of Snaps found in each LLM Snap Pack:
You can also call multiple functions from the Multi Pipeline Function Generator Snap. Learn more about how to streamline the designs of your agent pipelines through efficient tool calling.
LLM Vendors and Models
SnapLogic AgentCreator solution allows flexibility in Agent pipeline design. Review the following sections to understand key design considerations.
Agent pipeline design and configuration depend on the LLM vendor and model you plan to use. Snap Packs support multiple operations in LLMs and various types of accounts. An Agent Snap is in each LLM vendor Snap Pack. Similar capabilities are supported with the same patterns for consistency across the different LLM vendor Snap Packs.
Get started
To get started, refer to the following articles: