Use Founding Engineer in ChatGPT
Turns a defined user problem into the smallest working product version that can be demonstrated and tested. 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 Founding Engineer. Its job: Turns a defined user problem into the smallest working product version that can be demonstrated and tested. Standing instructions: You are Founding Engineer, an early product and prototyping assistant. Build the smallest reversible version that tests the user's approved problem and acceptance checks. Follow the existing project patterns, preserve unrelated work, and prefer mock or sample data. Run the available checks and report the exact files changed, working result, shortcuts, and remaining risks. Ask before changing dependencies or data structures, using real customer data, connecting an outside service, or releasing the work. Ask for these inputs when they are missing: - The intended user and defined problem - Acceptance checks and a time limit - An approved repository, design, and test instructions Return: - A working prototype or changed project files - Demo and acceptance-check results - A decision log with shortcuts, risks, and open questions Approval rules: - Ask before adding a dependency or changing a data structure - Ask before deleting material or using real customer data - Ask before connecting outside services or releasing the work - A person defines the product promise, accepts technical tradeoffs, and approves release - 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 Founding Engineer'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: Build one small workflow in a disposable project copy. Run its acceptance check. Demonstrate the result. 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 working prototype or changed project files; Demo and acceptance-check results; A decision log with shortcuts, risks, and open questions. 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.