Start with the job to be done

The working assignment is to choose and run a two-week AI career experiment instead of guessing a forever title for a teacher exploring product, operations, data, engineering, or governance work. That sentence is narrower than “use Careers in AI.” It identifies a deliverable and a reviewer. Write a definition of done with three layers: the output must satisfy the audience's need; factual or functional claims must be traceable; and a named person must own the final decision. Titles change faster than durable work. Optimize for evidence that you can perform a useful task, explain trade-offs, and learn from feedback.

Start by separating tasks. The model may draft, classify, transform, compare, or suggest. It may not silently approve, publish, grade, deploy, cite, or consent on someone's behalf. For this assignment the authoritative material is energizing tasks, transferable skills, constraints, current job descriptions, skill gaps, people to interview, and a project question. Anything absent from those inputs is either an explicit assumption or an unanswered question.

Use this prompt as a realistic starting contract:

I enjoy explaining hard ideas, interviewing people, and editing. Skills: classroom teaching, spreadsheets, basic research. Constraint: four hours weekly and no career break. Suggest three role-family experiments. For each: transferable evidence, one gap, a two-week portfolio artifact, and one professional to learn from. Do not predict salary or hiring probability without current sources.

Notice what the prompt does: it states the setting, limits the output, names forbidden behavior, and requests evidence that can be reviewed. It does not ask the model to “make it amazing.” If a constraint matters, make it testable. Replace “be accurate” with a source boundary, formula check, test command, rights ledger, or approval step.

A useful response would look like this: Three bounded experiments across AI education, product operations, and evaluation, each producing evidence rather than promising a job outcome. That description is intentionally observable. “Looks good” is not acceptance. The operator must collect five current job descriptions per path, count repeated requirements, interview a practitioner, inspect current labor sources, and evaluate whether the work itself fits. Keep the source material beside the draft so review means comparison, not memory.

Run the work through inventory → scan roles → choose experiment → build → interview → decide. Stop when an authoritative input is missing, a high-risk claim lacks evidence, private material cannot be safely removed, or the proposed action exceeds the permission granted. Escalation is successful workflow behavior, not model failure.

Common framing mistakes are chasing trendy titles; fabricated salary claims; treating course completion as evidence; ignoring domain expertise; building projects no target role values. Prevent them by writing a one-paragraph job card: user, decision, deliverable, source of truth, constraints, reviewer, and stop condition. This card becomes the anchor for every later prompt.