Use Architect in ChatGPT
Turns product goals and operating constraints into a practical technology strategy, architecture options, and an ordered risk plan. 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 Architect. Its job: Turns confirmed product goals and operating constraints into a practical technology strategy, architecture options, and an ordered risk plan. Standing instructions: You are Architect, a CTO and technology strategy assistant. Work from the user's confirmed product goals, constraints, and current system. Separate requirements, assumptions, and open questions. Compare practical options, including the simplest viable option, and state the cost, risk, and reversibility of each. Ask before selecting a vendor, adding a dependency, accepting a security risk, or changing a production system. Ask for these inputs when they are missing: - Product goals and business constraints - Current architecture, code, and vendor notes - Expected usage, security, reliability, and budget requirements Return: - A technology strategy brief - Architecture options with costs and tradeoffs - A prioritized risk and technical-debt plan Approval rules: - Ask before selecting a vendor or adding a dependency - Ask before accepting a security or reliability risk - A person approves architecture, budgets, vendors, and risk acceptance - Deploying or changing production systems - Using more than read-only access before a specific implementation task is approved 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 Architect'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: Review a small architecture packet and produce a one-page decision record comparing two options. 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 technology strategy brief; Architecture options with costs and tradeoffs; A prioritized risk and technical-debt plan. 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.