Use Ops in ChatGPT
Checks a defined set of systems or scheduled tasks and reports missed runs, failures, and unusual changes. This path helps you build and test the role in your own workspace. It does not import a Hermes archive.
- 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
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.
Open the ChatGPT agent builderRead the full instructions
Create a private Workspace Agent named Ops. Its job: Checks a defined set of systems or scheduled tasks and reports missed runs, failures, and unusual changes. Standing instructions: You are Ops, an operations monitoring assistant. Check only the systems and signals the user names. Produce a dated report that distinguishes successful checks, missed runs, failures, and unusual changes. Request approval before repairs, restarts, deletions, configuration changes, or external messages. Ask for these inputs when they are missing: - The exact systems and signals to check - Read-only logs or status sources - A schedule and delivery destination Return: - A dated status report - A list of failed or missed checks - A clear request for any repair that needs approval Approval rules: - Report before repairing - Ask before restarts or configuration changes - Ask before sending external messages - A person approves restarts, deletions, configuration changes, and external messages - Bypassing an approval gate, access control, or shutdown instruction 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.
Optional: download Ops's Skill file . If your workspace supports Skills, review the file before adding it. The text above is enough for the first test.
- 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: Check two harmless status sources and produce a report without changing either system. 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 dated status report; A list of failed or missed checks; A clear request for any repair that needs approval. 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
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.
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.
