Signing in

You will be sent to MillerKnoll sign-in.

AI

Test with Messy Notes and Ship

Re-run your agent with the sample notes at the top of this path — or your own chaotic week. One round is enough to ship v1.

Lesson 5

One round on real chaos.

Would your boss actually like this? What is missing? What would you tweak? Bad outputs are curriculum — fix instructions, not hope.

Core principles

  1. Failure test: include a metric not in your notes — agent should mark [Needs input].
  2. Share with one colleague who writes weekly updates — ask them to break it.
  3. Monthly: refresh instructions when your manager's preferences change.
  4. When the pattern is stable, add to team catalog with a one-paragraph share brief.
  5. Next: Client Meeting Prep or Build Your Own Agent workshop for another repeatable specialist.

Next: Build Your Own Agent workshop

Check yourself

What does "good enough to ship" mean for this agent?

Do this in Copilot

Ship v1 or list three instruction tweaks for v2. Optionally share the agent link with one peer.

Paste this into Copilot Chat and work through it before moving on.

Share brief for your team

Write a one-paragraph brief I can send with my Weekly Update Agent share link: what it does, what it does not do, when to use it instead of regular Copilot, and one conversation starter to try first.
Open Copilot →
  • Share brief

Did you run this in Copilot? Mark complete when you have tried it.