Skip to content
Page 9 of 9

Reflection 1

How This Reflection Works

Your Facilitator will pull from these questions to lead a cohort-wide discussion. If your AI assistant is building during a Challenge and you have a free moment, these also make great team conversation starters while you wait.

What You Built

  • Walk through your application. What's working? Where did you get further than expected, and where did you get stuck?
  • When you built different parts of your application, did the data structures stay consistent across them? Or did you discover that one component was storing or expecting data in a different shape than another? What happened when you tried to connect the pieces?
  • When you started working with the data, did its structure match what you expected? Were there surprises: nested fields, missing values, unexpected formats, or volume that changed how you approached the problem?

What You Practiced

  • How did the Three Pillars (Scope, Intent, Structure) show up in your delegation? Can you point to a specific prompt where being more specific produced a noticeably better result?
  • Did you write user stories with acceptance criteria before delegating, or did you fall back to plain-English requests? What was the difference in what you got back?
  • When you verified against your acceptance criteria, did you catch something that "looked done" but actually wasn't? What did that tell you about the value of having a definition of "done" before you start?
  • Did you hit a spinning loop, re-prompting two or three times without getting closer to what you wanted? What broke the loop: tighter criteria, a smaller task, or a fresh conversation? What does that tell you about where the problem usually lives?
  • Did you catch yourself slipping into "just get output" mode, accepting whatever AI gave you and moving on? Or were you practicing the tools: small tasks, clear acceptance criteria, verifying before continuing? If you had to build something for your real job where the details truly mattered, which mode would serve you better?

How You Worked

  • How did your team organize? One driver and three navigators, pairs on different features, something else? What would you keep and what would you change for Challenge 2?
  • Did your project context file help during the challenge? Did AI seem to "know" your project, or were you still re-explaining things?
  • When AI produced a working feature, did you stop to understand how it worked, or did you accept it and move on? There's a difference between building with understanding and just accepting output. Which did your team do more of, and what does that mean for your ability to build on it in the next challenge?

Looking Ahead

  • You've probably noticed that every time you ask AI to build something similar (a table, a detail view, a filter), it comes out slightly different. The data model drifts. The styling is inconsistent. What would it take to make AI produce consistent results for repeating patterns?