Part 4 of 4 | Build the workflow that runs your AI job again and again
You've already taught AI how to do this job.
But you’re still manually feeding it the input you need to process every time.
How about we take that off your plate too?
Say your job is writing follow-up notes after client calls, and you drop the call transcripts into a folder.
Right now, running the job means dragging that file into Codex yourself.
Once you build a repeatable workflow, you just type one line, the AI looks through that folder, grabs the file, does the job, and sends you a link to the result when it's ready to review.
That's what this workflow gives you:
A place for new information (which the AI will automatically look at)
A place for the finished result to wait for your review
In this last part of the guide, you'll build that workflow around the Skill you saved in Part 3.
By the end, you’ll have a tested repeatable workflow for the job.
You can just name the next case, start the run, and know where to find the result when it’s ready.
Step 1. Try the Skill on a different case
You’ve run the job once.
But how confident are you that it can handle different cases in the future?
Only one way to find out. Let’s test it out with a second case.
Open a fresh chat under the same project.
Pick a second case that's really different.
For a client recap, use another call with different people and different decisions.
For a feedback report, use another period with different comments.
Attach the new input, paste in the relevant text, or point the AI to the exact file in the project.
If you’re not sure what to hand over, check the "I will use" line on your job card. If the job needs multiple files, bring all of them.
Now, use the starting request saved in your job card.
Don't repeat the preferences and corrections you already locked in during the previous part.
This is your chance to see if the saved Skill carries your saved corrections into new cases.
Open the full result and check it against the new source and your job card:
Does it include everything this job is supposed to produce?
Do the names, dates, and facts actually belong to this case (and not the first one)?
Did AI apply the reusable corrections you confirmed in Part 3?
Did it run the saved checks and flag anything it wasn't sure about?
If something's off, call it out the same way you did in Part 3.
Answer whatever's in "What you decide," and keep revising until you're happy with the result.
Tell the AI when you accept it, and have it save that version.
Step 2. Decide how you want the workflow to work
You’ve now run this job twice.
The Skill knows what to do, but you’re still handling some of the boring parts around it.
You have to supply the input yourself.
Finished work can stay buried in Codex unless you move it somewhere else.
A repeatable workflow takes care of that setup.
It tells the AI where to find the case you name, where to put finished work, and what to do when something goes wrong.
You still start the job yourself and review the result before anything else happens.
Ask AI to show the current workflow
Before changing anything, ask AI to show you how the job works right now.
Ask the AI to show you the workflow, using the "Make my job repeatable and automatic" Skill.
(that’s one of the AI Brain’s starting skills. The AI will know what to do.)
The AI should come back with something like this:
BTW, “Route” here means your job’s workflow.
Do a quick check that the AI is using the saved Skill you tested in Step 1.
Then look at where it gets the input and where it saves the finished result.
You’ll probably see that some parts of the workflow still need you to do things yourself.
That’s what you’ll fix next.
Tell AI what you’d like to change
Right now, we’re going to tell the AI:
where to find new files
where to log every run so you (or the AI) can diagnose issues later
where to save the finished results.
Choose a source that fits the way you already work.
If the information is in your downloads folder, point AI there or have it create new folders in there.
For my examples on this part, Imma use Input, Runs, and Review, respectively.
Here’s a sample prompt, if you want to copy it:
Update the workflow for this job to use three new folders directly under my Downloads folder: Input, Runs, and Review.
When I name an input, get that exact file or file set from Input and leave the source unchanged. Run the saved Skill for this job.
If the job finishes successfully, save every required result in Review and create a dated run receipt in Runs that identifies the input, results, and checks.
If that exact input has already completed this workflow, stop and point me to the earlier result instead of creating another one.
If the job cannot finish because information is missing, a check fails, or something else blocks the run, keep unfinished work out of Review. Explain what stopped the job and what I need to fix. Record the failed attempt in Runs.
Keep the workflow manual. Do not connect an app, create a schedule, run the job, or change anything outside this project.
Show me the complete updated workflow before I activate or test it.
The AI should come back with an updated workflow:
You should be able to tell where the next input goes, what starts the job, where a successful result will end up, and where to look if a run stops.
Check for the newly created folders too.
Step 3. Run the workflow on a new case
Now let’s test if that custom workflow works.
Give it a brand new case, one it hasn’t seen before.
Make sure the new file is in your designated source folder.
Send your one-line request and name that file.
Open the finished result in your designated review folder.
Check the result before accepting it.
If that all works the way you expect, you’re done testing.
This is the workflow you’ll use for every future case of this job.
That's the whole build, done
Nice work setting up your first job with the AI Brain.
From here on, your AI Brain works more like a personal agent for this part of your work.
It uses the context you’ve already given it, follows the Skill you’ve saved, and improves when you save a confirmed correction.
When you’re ready to set up another job in the same project, you already have a head start.
The business context you’ve already saved carries over.
Ask the AI for a fresh batch of job ideas (or just tell it the one you already have in mind).
Set the standard for that job, build its Skill, then test its repeatable workflow the same way you did here.
I’m curious what you build next.
Optional help
AI can describe the workflow but can't run it
Ask what's blocking it and what it needs.
It might read the source just fine but have no way to actually run the Skill, or nowhere to save the result.
Ask AI for the simplest setup that works with the information you've supplied.
You can still use the saved Skill manually, like in Step 1, while you sort this out.
Treat the workflow as untested until it has completed the job + you've opened and checked the saved result.
The duplicate rule is blocking a revision you actually want
The AI Brain Starter has a built-in duplicate rule that stops it from doing the same job cases.
In case that rule kicks in while you’re trying to revise something, tell AI which result you're revising and what's changed.
Ask it to keep the earlier version and save the revision separately.
Once you've agreed on that, have it run the job again and review the new result.
Check the proposed result path.
An intentional revision needs a clear record so you can tell it apart from an accidental duplicate later.
A run stops halfway through
Ask what AI created and where it saved each item.
Have it keep the unfinished work out of Review, preserve any already-accepted results, and tell you exactly what needs fixing.
Once you’ve resolved the problem, approve the retry and review the complete result.
Let the AI keep the failed attempt in the record so you can tell which attempt eventually passed.
Your input files are in an app
You can begin with an export or pasted text.
If you'd rather have AI get the information directly, ask it whether your app has a supported connection, such as an MCP connection or API, and what setup it would need.
You'd rather review the result somewhere else
Use it wherever you already check that kind of work.
A new dashboard is just one more inbox to forget about.
For a doc or page in another app, ask AI if it supports an MCP connection or API to that app.
If it does, give it the exact destination and who can access it.
You want the job to start on its own
Maybe you want the job to start on a certain schedule or a certain trigger event.
If the current workflow works cleanly, that kind of automation sounds like a good idea.
Ask the AI how you can set it up.
Be clear on the trigger, the input, and where you'll review it. Also check any account access or running costs before you set it up.
Before leaving it to run on its own, have AI help test what happens if the input is missing, the same case arrives twice, or a run stops halfway through.
Check how to pause it too, then make sure pausing actually stops new runs.
You also decide whether sending or publishing should wait for your review or happen automatically.
If you want automatic delivery, agree on exactly what may be sent or published, where it goes, and when AI should stop and ask you.
That needs its own setup and test before you enable it.
