AI Conductor Academy

Core: 0 of 6 done

Capstone Lite About 18 min ← All modules

Core · Module 4

Capstone Lite

Course outcome 4Project 3: lab spec

Design a short, self-paced practice lab that an AI agent could build as a microsite activity. You’ll write the prompt, how success is measured, and how learners check themselves.

Big question How do you teach a workflow that an AI agent can also execute and improve?

Note: The checks confirm your spec has the structure an agent needs. They don’t build or run the lab.

By the end of this module, you’ll be able to:

  1. Design a self-paced practice lab spec with a clear prompt, measurable success criteria, and a self-check learners can run without an instructor, all structured so an AI agent could build it.

How you’ll show it: Project 3, your lab spec (download). The examples come first. Course outcome 4 of 6

What good looks like

This is the bar each part needs to reach (Meets). You’ll get feedback on each part when you check your work.

  • Prompt: tells learners exactly what to do (match, choose, complete…) in a named lab pattern, in 60+ characters.
  • Success criteria: something the learner can check themselves, like a score or pass/fail.
  • Self-check: learners can check their own work without an instructor, using an auto-score or checklist.

How you pass: all three parts at Meets or better, after you’ve read the example. This is the last Core module.

The automatic check looks for a few signals of these. It can’t judge quality, so aim for the description, not the keywords.

Warm-up: quick recall

Two quick questions from earlier modules. Pulling ideas back from memory helps them stick. This is just for practice and isn’t scored.

Start with an example

Example

Match an enablement use case to a Grok Bot surface

  • Prompt: “In this match lab, learners pick the best-fit Grok Bot surface (Agents, Channels, Computer, Routines) for five enablement scenarios. Use keyboard or pointer. Aim for at least 4 of 5 correct.”
  • Success criteria: “≥4/5 correct matches; each incorrect answer shows a text rationale naming the correct surface.”
  • Self-check: “Auto-score JSON answer key vs learner selections; display Correct/Incorrect text per item; allow one revision.”

A second, shorter example (checklist pattern): Prompt: “Complete the 6-item checklist lab to review your agent brief before you share it.” Success: “All 6 checklist items marked pass.” Self-check: “Each item auto-checks the matching field and shows why it passed or not.”

What not to do: a prompt of “Make a fun lab”, success that “feels engaging”, and a self-check of “ask an instructor”.

Your project: a lab spec

Read the example above to open this form.

Lab spec
Start with a verb, like “Match…” or “Write…”. It’s included in your download so whoever builds the lab knows what it’s for.
Tell the learner what to do (match, choose, complete…) and mention the lab, form, or checklist. 60+ characters.
How does the learner know they succeeded? Make it checkable. 40+ characters.
How can learners check their own work without an instructor? Try a checklist or an auto-score. 30+ characters.

Tip: Feedback is automatic. It looks for specific details, like a number, a named owner, or a “when”. It’s a quick check, not a grade.

Download as

Next: see your Core summary → ← All modules