Skip to content

Flow Super Agent

The FlowSuperAgent in the AI Refinery SDK is designed to designed to orchestrate complex workflows composed of multiple utility agents with defined dependencies. The FlowSuperAgent allows users to define nodes (utility agents) and edges (dependencies) between them, enabling the creation of flexible and powerful pipelines.

Workflow Overview

The FlowSuperAgent is invoked by the orchestrator for complex tasks that are defined by the user as directed graphs. Upon invocation, the FlowSuperAgent workflow is structured around three essential components:

  1. Goal: The overall goal that the FlowSuperAgent needs to accomplish by following the deterministic workflow defining the action steps.

  2. Agent List: A FlowSuperAgent has access to a pool of utility agents (e.g., SearchAgent, AuthorAgent, etc.) that it directs to accomplish the overall goal.

  3. Workflow Graph Definition: The graph dictating the workflow of the FlowSuperAgent that defines the dependencies between the utility agents to schedule the task execution.

Usage

Flow super agents can be easily integrated into your project by adding the necessary configurations to your project YAML file. Specifically, you need to:

  • List your super agents under the super_agents attribute in your project's YAML configuration.
  • Ensure the agent_name you chose for your super_agents are listed in the agent_list under orchestrator.
  • Ensure that the assistant agents that are available to the FlowSuperAgent are listed as agents in the utility_agents list.
  • Define the deterministic workflow as a graph with edges and vertices. To do so:
    • Define the vertices as entries in the agent_list of the FlowSuperAgent
    • Define the edges by specifying for each agent_name in the agent_list the next_step that will be taken.

Quickstart

To quickly set up a project with a FlowSuperAgent, use the following YAML configuration. In this setup, we have a single flow super agent that acts as Strategy Advisor. It has three instances of a SearchAgent and one of the AuthorAgent in its agent pool. You can add more super agents and utility agents as needed.

utility_agents:
  - agent_class: AuthorAgent
    agent_name: "Brief Writer"
    agent_description: "Write the marketing brief"
    config:
      memory_attribute_key: "plan"
      title: "Insights Brief"
      leading_questions:
      - question: "What is the name of the project?"
        prompt: "Project name. This is usually specified by the background information."
      - question: "Who is the audience?"
        prompt: "Who exactly are we targeting? Detail the specific demographics, industries, or roles we aim to reach, emphasizing how our project aligns with their interests and needs."
      - question: "What do they want to do and why?"
        prompt: "What are the audience's main objectives and motivations? Let's dive into their goals to understand how our project aligns with their needs, rather than focusing on our growth targets."
      - question: "How can we help them?"
        prompt: "What specific support or solutions can we offer to meet the audience's needs? Propose a range of options for discussion."

  - agent_class: SearchAgent
    agent_name: "Competitor Researcher"
    agent_description: "Find what our competitors have done in the area / industry."

  - agent_class: SearchAgent
    agent_name: "Campaign Insights Researcher"
    agent_description: "Find insights and takeaways from other past campaigns that are relevant to this topic"

  - agent_class: SearchAgent
    agent_name: "Audience Understanding Researcher"
    agent_description: "Identify the potential audience for this campaign focusing on their desires, concerns, and needs"


super_agents:
  - agent_class: FlowSuperAgent
    agent_name: "Strategy Advisor"
    agent_description: |
      The strategy advisor can help user write their marketing campaign brief. Only call this agent when the user explicitly asks for a brief.
    config:
      goal: |
        The goal is to create an insights brief for a marketing campaign at Accenture. To create the brief, you will need to call the research agent to do research around the topic. Make sure you have called all the agents (you can track the call history from below) before you call the author agent to draft an insights brief.

      agent_list:
        - agent_name: "Competitor Researcher"
          next_step:
            - 'Campaign Insights Researcher'
            - 'Audience Understanding Researcher'

        - agent_name:  'Campaign Insights Researcher'
          next_step: 
            - 'Brief Writer'

        - agent_name:  'Audience Understanding Researcher'
          next_step: 
            - 'Brief Writer'

        - agent_name: "Brief Writer"

Template YAML Configuration of SuperAgent

In addition to the configurations mentioned for the example above, the FlowSuperAgent supports several other configurable options. See the template YAML configuration below for all available settings for each super agent.

agent_class: FlowSuperAgent # The class must be FlowSuperAgent
agent_name: <A name that you choose for your super agent.> # Required. 
agent_description: <Description of your super agent.> # Optional.

config: # Required. Configuration of this super agent.
  goal: <A high level goal of your super agent.> # Required
  steps: <The steps that should to be followed by the super agent.> # Required
  exit: <The name of the exit agent> # This agent generates the final output once all tasks in the checklist is completed. Must be one of the agents in the agent pool i.e., `agent_list` (see below).

  agent_list: # Required. The list of agents to be added in the agent pool. Each agent listed here must be configured under `utility_agents` in the root of project YAML file.
    - agent_name: <Name of agent 1>  # Required. 
      next_step: # Optional. If provided, these will be the tasks that depend on the execution of the current one and will be run after this step is completed (next nodes in the workflow graph). If not provided, this step does not set any dependedny for the next ones (node in workflow graph does not have other nodes it connects to) 
        - <Name of Agent 2>
        - <Name of Agent 3>

    - agent_name: <Name of agent 2>  # Required.
        next_step:  <Name of agent 3>

  agent_concurrency: 3 # Optional. Number of maximum parallel thread workers for execution. Defaults to 5.

  magic_prompt: "" # Optional. Template for generating prompts for nodes. Defaults to a predefined prompt. 

  llm_config:
  # Optional. Customized llm config (if you want the Flow SuperAgent to use a different LLM than the on in your base config)
    model: <model_name>