Lesson 6 — Discernment for code
Course: AI Fluency for Builders (the AI Architect path, Course 1) Section: 4 — Discernment for builders Lesson: Discernment for code Estimated time: 30 minutes (video: 5 minutes) Source: Official Skilljar course material (user-provided) License: Copyright 2026 the AI provider. Developed in partnership with CodePath, building on the AI Fluency Framework by Prof. Rick Dakan (Ringling College of Art and Design) and Prof. Joseph Feller (University College Cork). Released under CC BY-NC-SA 4.0. Note: This is the original English source text, lightly reformatted (headings and paragraph breaks added) for study. No wording has been changed. Interactive UI elements are reproduced as lists, with a note marking them as interface content. Coverage note: In the source provided, only Lens 1 includes an expanded definition. Lenses 2–5 appear by title only. Counterpart translation: 08-第6课-Discernment-for-code.md
What you'll learn
Estimated time: 30 minutes
By the end of this lesson you'll be able to:
- Evaluate AI-generated work across five lenses: correctness, quality, fit, experience, and responsibility
- Raise your quality bar beyond "it works" by learning failure modes specific to AI-built products
- Catch AI's predictable technical blind spots before they reach production
Discernment for code
(5 minutes)
When AI can spin up a working product in minutes, "working" stops being the bar. You'll learn where AI-built products typically fail, the technical blind spots that surface in production but not in development, and how to build the taste that AI doesn't have.
The Five Lenses of Discernment
Lens 1 is easy to test — run it and see. By Lens 5, you're making judgment calls AI can't make for you.
[Interface element] The following are the five lens tabs as shown on the page.
- Lens 1 — Functional Integrity
- Lens 2 — Production Readiness
- Lens 3 — Problem Fit
- Lens 4 — Experience Quality
- Lens 5 — Responsible Impact
Lens 1 — Functional Integrity
Does it work?
✓ Produces correct output for real inputs, not just test data
Common AI failure Code that passes unit tests but breaks on real data the prompt never covered
Key takeaways
- Code that runs can still fail. The default AI output is technically complete but often misses the point.
- AI has predictable blind spots in concurrency, security, and anything that only breaks at scale.
- Taste is a builder skill. AI delivers functional. Making it worth using is on you.
Exercise — User testing the Clinic project
Put your build in front of a partner playing a patient or clinic admin — don't explain, don't help. Watch where they get confused, what they ignore, and what they wanted that you never built. Write down three things you'd change and which lens each falls under.
Lesson reflection
- Which of the five lenses do you naturally apply, and which do you have to remind yourself to check?
- When AI produces something that isn't good enough, what's your instinct: fix it yourself, or describe it better?
What's next
You've stress-tested the Clinic Wait Time Checker through the lenses you tend to skip. Next, you'll look at the same tool through a different lens: how does it actually feel to use?
Feedback
As you progress through the course, we'd love to hear from you about how you are using concepts from the course in your work, plus any feedback you may have. Share your feedback here.
Acknowledgments and license
Copyright 2026 the AI provider. This course was developed in partnership with CodePath, building on the AI Fluency Framework developed by Prof. Rick Dakan (Ringling College of Art and Design) and Prof. Joseph Feller (University College Cork). Released under the CC BY-NC-SA 4.0 license.