Creating a Supervisor agent

Hitachi iQ Studio User Guide

Version
1.0.x
Audience
anonymous
Part Number
MK-26HIQS001-00
ft:lastEdition
2026-03-31

Create a supervisor agent that coordinates multiple worker agents.

  • Make sure you have Administrator or Agent Builder permission.
  • Open knowledge base and check that each required collection displayed a green checkmark.
  • Verify that the necessary MCP servers are registered.
  • You have prepared your summarizer prompt (role definition) and know which agent(s) to use.
  1. On the iQ Studio home page, go to AI Agents and click Create.
  2. On the Create an AI Agent page, select Supervisor agent type.

    The following table describes the additional information required to create a new supervisor agent.

    Field Description
    Type Select the Supervisor agent type.
    Import Agent (.json): Upload a JSON file that defining the supervisor agent’s configuration, including its roles, tools, workflows, and permissions. After you upload the file, the system reads the configuration and installs the agent.

    Note: Use this option only if you have previously exported an agent as a JSON file.

    Name Human-readable agent name.
    Description Short summary of the agent’s purpose.
    Summarization Instructions You synthesize research into executive sales intelligence to win business. Rules: No fabricated URLs. Focus on actionable insights to accelerate deals & boost win rates. Advise like a revenue-focused executive. Look for any interesting insights about persons, their ideologies, and political inclinations.
    Avatar Optional image representation.
    Avatar dropzone You can use a custom image. The supported file types are JPG, JPEG, JFIF, PJPEG, PJP, PNG, SVG, and the maximum file size must be under 1 MB.
    Advanced options* Optional settings used to control agent limits and behavior.
    Summarization Model Model that distills the source content into concise, coherent summaries preserving key points, structure, and tone while removing redundancy; configurable for length, detail, and style.
    Summarization Model Max Tokens Sets the maximum number of tokens the summarization model can use in a single response. Controls output length.
    Summarizer Prompt Instructions provided to the summarization model that defines persona, capabilities, and desired output style or format.
    Planner model A model responsible for breaking high‑level tasks into ordered subtasks and assignment plans for agents.
    Planner Max Tokens Token budget allocated to the planner model for generating plans; limits plan length and detail.
    Planner Prompt Instructions for the planner model to break tasks into subtasks and create an task plan.
    Orchestrator Model A model that combines, reconciles, and synthesizes outputs from multiple Workers into a coherent final result, resolving conflicts and ensuring consistency with goals and constraints.
    Orchestrator Model Max Tokens Token budget for the orchestrator model; determines how much context and how detailed the final synthesis can be.
    Orchestrator Prompt Instructions for the orchestrator model to combine and refine outputs from supervisor agent and create the final result.
    Note:* Leave advanced options at default unless you need custom control policies.
  3. Click Next.
  4. On the Equip page of the Build a Supervisor AI agent wizard, add one or more agents that you created.
  5. Click Next and then click Done.
  6. Confirm that the new supervisor agent appears in the AI Agents list on the AI Agents page.