The last studio. You'll write a few inputs the agent must handle correctly, a few it must refuse, and a small first-week ritual to catch surprises. Then you'll earn the last sticker.
Testing is the unglamorous part. Almost nobody does it. The agents that survive past month 3 are the ones whose authors spent a calm hour writing tests before wiring anything live.

3-5 real input cases where you already know the correct output. These are the agent's exam. If it passes them, it earns the right to run.
→ Use real data shapes from your business, not invented ones.
Try to break it on purpose. Missing fields, corrupted data, weird edge cases, holidays. If the agent doesn't refuse cleanly, your guard isn't strong enough.
→ The goal isn't to pass these. The goal is to fail correctly.


Run the agent for a week with the "post" step pointing at a private channel only you can see. Check every output. Don't go live until you've sampled at least 5 in a row that you'd have sent yourself.
→ A week of dry-run saves a month of cleanup.
For the first 5 working days after launch: read every output. Note anything that surprised you. After day 5, decide: keep, fix, or kill.
→ Most "the agent went rogue" stories happen because nobody read week 1.

Auto-saved. Exportable. Pair it with your spec and instructions to hand off a complete build packet.
Saved automatically. Combined with your spec (Studio 07) and your instructions (Studio 08), you now have a complete build packet for one real agent.
Most people who start a guide like this never finish it. You did. Here's the only thing left to say.
You walked through the whole workshop. You have a spec, instructions, and tests for one real agent. Now go build it. Start small. Run it in draft mode. Read every output for a week. The boring ones win. I'll be at the bench when you're ready for the next one.
The final sticker. The whole set.