Edessa

Run your SOP inside ChatGPT

Last updated: October 3, 2026

A common way to run a process through ChatGPT is to paste it into the chat, then paste it again tomorrow. That works once. It does not compound, and it quietly drifts every time somebody re-pastes a slightly different version.

A project fixes that. The process lives in one place, every chat inside the project can see it, and there is one copy to update.

What can ChatGPT read?

ChatGPT projects hold related chats, uploaded reference files and their own instructions together, and those project instructions override your global custom instructions inside that project. You can attach documents and spreadsheets, or paste text.

So the shape that works is: the workflow file as project reference material, and a short project instruction telling ChatGPT to follow it.

The details move, so check OpenAI’s help article on projects rather than a blog post. The install steps were checked against the vendor docs on October 3, 2026.

Where does the file go?

  1. On ChatGPT Business, Enterprise or Edu, upload the Skill zip directly: in the sidebar choose Plugins, open the Skills tab, select Create, then Upload from your computer. On other plans, use a project:
  2. Export the workflow as Markdown, or as a Skill and use the SKILL.md inside the zip. Either is plain text.
  3. Create a project in ChatGPT, then attach the file as reference material.
  4. Add a project instruction naming it, something like: "Follow the attached workflow exactly. Ask before you deviate."
  5. Start a chat inside the project and ask for the task. If ChatGPT ignores the file, check the project instruction before you change the file.
Try Edessa free

Three asks worth trying

Once the process is loaded, the useful prompts are not “summarise this.” They are the ones that use the fact that ChatGPT can now see how your business actually works.

  • "Walk me through this process for today's job and stop before the last step." Keeps the send, the charge or the submit in your hands while the rest gets done.
  • "Which steps here need a decision, and which are just typing?" The typing steps are your automation shortlist. The decisions are the ones to leave alone.
  • "Rewrite this as a checklist someone could follow on their first day." A useful second artifact from the same file, and a fast way to see what your write-up assumes.

How do you keep it current?

This is where documentation goes stale. The process changes, the file does not, and six months later the skill is confidently wrong. Keeping it right by hand means editing a Markdown file every time a step changes.

The alternative is re-recording. Do the task once the new way, replace the file with the new export, and the thing your AI tool reads matches what you actually do. That takes about as long as the task does.

The recording method is here, including the manual version if you would rather not use a tool for it.

Who wrote this. Thaddeus Demeke, Founder of Elevaite and the founder of Edessa. Five years at Genentech, most recently as a Senior Data Scientist, then building AI systems inside small businesses across agencies, home services, real estate and ecommerce. I run my own processes this way.

See how the AI SOP generator works

Related reading

© 2026 ElevaiteWorks LLC. A product of Elevaite.