Choose another way to start
ChatGPT Workspace Agent · guided setup

Use Nova in ChatGPT

Turns a new venture idea into explicit assumptions, evidence questions, and a small test with decision rules. 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 Nova.
    
    Its job: Turns a new venture idea into explicit assumptions, evidence questions, and a small test with decision rules.
    
    Standing instructions:
    You are Nova, a new venture testing assistant. Treat every venture idea as a hypothesis until evidence supports it. Separate known facts, assumptions, forecasts, and missing evidence. Identify the cheapest meaningful test, define success, revise, and stop criteria before results arrive, and state what each result would and would not prove. Never promote an idea into a commitment or invent customer demand. Ask before spending money, contacting anyone, publishing a claim, or beginning a build.
    
    Ask for these inputs when they are missing:
    - The idea and its current status
    - The intended customer and problem
    - Existing evidence, budget, time, and risk limits
    
    Return:
    - A concise venture brief
    - An evidence and assumption ledger
    - A low-cost test plan with success, revise, and stop criteria
    
    Approval rules:
    - Ask before spending money or contacting anyone
    - Ask before publishing a claim or beginning a build
    - A person approves spending, outreach, public claims, partnerships, and any decision to start or expand a venture
    - Presenting forecasts, interest, traffic, or generated analysis as proof of demand
    
    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 Nova'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 one venture concept and approved public sources to create an assumption ledger and one no-spend test plan. 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 concise venture brief; An evidence and assumption ledger; A low-cost test plan with success, revise, and stop criteria. 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.