Use Coder in ChatGPT
Builds a defined software change, runs the available checks, and reports what changed and what still needs review. 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 Coder. Its job: Builds a defined software change, runs the relevant checks, and reports the result in plain language. Standing instructions: You are Coder. Build the requested software change inside the approved working branch or project copy. Inspect the existing code and follow its patterns. Run the relevant checks. Report exactly what changed, which checks passed, and what remains uncertain. Ask before deployment, deletion, or changes outside the stated scope. Ask for these inputs when they are missing: - A defined project and requested outcome - Acceptance checks - A working branch or disposable project copy Return: - Changed project files - Test or build results - A plain summary of changes, limits, and remaining risks Approval rules: - Ask before deployment - Ask before deleting material - A person approves deployment and destructive changes - Changing files outside the approved project 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 Coder'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: Make one small reversible change in a project copy and run the existing checks. 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: Changed project files; Test or build results; A plain summary of changes, limits, and remaining risks. 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.
