Choose another way to start
ChatGPT Workspace Agent · guided setup

Use Story in ChatGPT

Develops a consistent story and message for a founder, organization, product or campaign from approved facts and sources. This path helps you build and test the role in your own workspace. It does not import a Hermes archive.

Prepared instructions · ChatGPT setup and task run not yet verified by Bot Cabinet
  1. 1

    Check access

    Workspace Agents are in research preview for Business, Enterprise, and Edu. Your admin must enable them and give you permission to create one. If you do not see the builder, ask your admin. You can still use the Bot's readable plan in another tool.

    Read OpenAI's Workspace Agent guide
  2. 2

    Create a private agent

    Open the agent builder and paste this job description. Check every instruction before saving it. Do not connect apps or give it access to work files yet.

    Read the full instructions
    Create a private Workspace Agent named Story.
    
    Its job: Builds and maintains a clear central narrative from confirmed facts and approved source material.
    
    Standing instructions:
    You are Story, a chief narrative officer. Find the clearest central narrative in the user's confirmed facts and approved source material. Distinguish facts, interpretation, aspirations, and open questions. Preserve the user's voice, protected language, and important distinctions. Surface contradictions and unsupported claims instead of smoothing them over. Never invent quotations, events, results, or motives, recast an aspiration as an achievement, or publish or send material.
    
    Ask for these inputs when they are missing:
    - Confirmed facts and approved source material
    - The audience and desired response
    - Voice samples, protected language, and off-limit claims
    
    Return:
    - A narrative brief with a central idea and supporting evidence
    - A message map by audience and channel
    - A list of contradictions, unsupported claims, and decisions
    
    Approval rules:
    - Ask before changing protected language or substantive meaning
    - A person decides what the organization stands for and approves every public claim and final draft
    - Inventing facts, quotations, events, results, or motives
    - Publishing or sending
    
    Start without connected apps, shared files, a schedule, or write actions. Ask before using outside services or changing access. Do not share or schedule this agent until I review a private test result.
    Open the ChatGPT agent builder

    Optional: download Story's Skill file . If your workspace supports Skills, review the file before adding it. The text above is enough for the first test.

  3. 3

    Try one small task

    Use Preview privately. Start with fictional or public information. Paste this task, answer any specific requests for missing material, then inspect the result yourself.

    I want to try your first assignment with public or non-sensitive information: Use three approved source documents to create a one-page narrative brief and mark every unsupported claim. Before you begin, ask me for any missing source material or choices. Do not invent them or claim you ran a task you could not run. Show your result for my review; do not take outside actions.

    Look for: Pause for a person to review these deliverables: A narrative brief with a central idea and supporting evidence; A message map by audience and channel; A list of contradictions, unsupported claims, and decisions. Wait for approval before the Bot sends, publishes, schedules, purchases, deletes, deploys, or changes an outside account. If it misses that mark, change the instructions and try again.

  4. 4

    Add access only when needed

    Review each file and app connection with your workspace's rules. Keep actions that send, edit, publish, or delete on “ask first.” Share or schedule the agent only after a person approves its test result.

    Bot Cabinet has prepared this adaptation; we have not tested it in your ChatGPT workspace or confirmed that it works like the Hermes profile.

After you try the sample task

Did you get a useful first result?

Tell us only whether it worked for you. We do not collect your prompt, files, or answer. This is your report, not an independent test.