Skip to lesson
Exit
The Onsite Build & Product Craft1 / 3

2 min lesson

What a good pick looks like

Work through the cases in "What a good pick looks like", pairing each signal with the move that fits.

Step 1 of 3

What a good pick looks likethree filters, applied fast

Real

A pain an actual Cursor user feels weekly.

You can name the user and the moment.

Not a feature in search of a problem.

Valuable

Moves a metric the team would care about.

Fits where the product is heading.

You can say why it matters in one line.

Shippable

A demoable slice fits in the time box.

Reuses primitives already in the repo.

Has an obvious narrow first version.

PICKING WHAT TO BUILD

Interactive diagram. Tab through its regions; each focused region shows its detail in the panel below.

diagram: quadrant

Aim for the top-left: real, valuable pain you can demo in the time box. Effort here is your build cost against the clock.

Learn more

Full explanation

Reading a deliberately vague prompt

  1. 1Pick the user moment. Name a specific person doing a specific task in Cursor - reviewing a big AI diff, hunting a bug, onboarding to an unfamiliar repo. Write the moment in one sentence.
  2. 2Write the problem statement. One crisp line: who hurts, when and why the current product makes it annoying. This is what you'll open your presentation with.
  3. 3List assumptions out loud. Scope, target user, what you're explicitly not building. Putting them on paper makes your judgment legible and lets the team correct you cheaply.
  4. 4Define the demo. Decide the single end-to-end path you'll show before you write a line. The build exists to make that path real.
  5. 5Send your clarifying questions. Slack the team the way you would on the job - share your plan, ask the two questions that actually change your design, then start.
Learn more

Optional practice

Practice: What a good pick looks like

QWhy is the onsite prompt deliberately vague and what does that tell you about how to spend your first hour?