Course Challenge
Module 5 · Diligence

Course Challenge

Bring the four competencies together: a scenario-based knowledge check, then a capstone in which you take one real coding task through Delegation, Description, Discernment, and Diligence with Claude Code.

How the Challenge Works

The challenge has two parts:

  1. Knowledge check: ten scenario questions covering every module. Aim for at least 8 out of 10. If you miss one, read the explanation and revisit that lesson.
  2. Capstone task: take one real task from your own work through all four Ds with Claude Code, and keep a short log as you go.

This course is free and self-paced, so there’s nothing to submit. The goal is a way of working with agents that lasts longer than any particular feature.


Part 1: Knowledge Check

🧠 Knowledge Check

1. (Module 1) A teammate says Claude Code is 'just ChatGPT in the terminal.' What's the most important difference they're missing?

2. (Module 1) After a read-only 'explain the codebase' session, git status shows a modified file. What should you do?

3. (Module 2) Which task should you NOT hand to the agent in high-autonomy mode?

4. (Module 2) You keep clicking 'allow' for npm test fifty times a day. What's the fluent fix?

5. (Module 3) Your brief says 'make checkout faster.' The agent rewrites the cart UI. What was missing?

6. (Module 3) Every session, you remind the agent not to edit files in src/generated. Where should that instruction live?

7. (Module 4) The summary says 'all tests pass,' but git diff --stat shows a test file with 40 lines removed. What's your next step?

8. (Module 4) After an hour, the agent keeps alternating between two broken fixes. What's the best move?

9. (Module 5) You ask Claude Code to summarize a third-party web page, in a session that also has your cloud credentials and an MCP tool that can send messages. What's the main risk?

10. (Module 5) A reviewer asks why your agent-written function handles the empty-list case that way, and you don't know. What does diligence call for?


Part 2: Capstone, One Task Through the 4Ds

Choose a real, medium-sized task from your own work: a bug with a reproducible failure, a small feature, or a refactor of one module. Keep a short log in a text file as you go.

🧪 Try It: Delegation: Decide and Set the Dial
  1. Write the task in one sentence.
  2. Answer the three delegation questions: Is it verifiable? Is it sized for review? Is a mistake reversible?
  3. Decide which parts you’ll delegate, which you’ll do together (augmentation), and which you’ll keep.
  4. Choose a permission mode and any allow, ask, or deny rules for this task. Write down why.
  5. Create a branch (or worktree) and confirm a clean git state.
🧪 Try It: Description: Brief It
  1. Check that your CLAUDE.md has the exact test and lint commands. Update it if not.
  2. Write a four-part brief: goal, context (with @ file references), constraints, and done.
  3. Start in plan mode. Review the plan with the Stage 1 questions from module 4 and push back at least once if anything is off.
  4. Log what you changed in the plan and why.
🧪 Try It: Discernment: Review Like You Mean It
  1. Let the agent execute. Interrupt if it drifts, and log each interruption.
  2. When it finishes, run git diff --stat before reading its summary.
  3. Read the full diff and check it against the failure-mode field guide from module 4.
  4. Run the key verification yourself.
  5. Ask a fresh session to review the diff skeptically. Log anything it found that you didn’t.
🧪 Try It: Diligence: Ship It Responsibly
  1. Run your personal shipping checklist from the last lesson.
  2. Scan the diff for secrets, debug output, and unrelated changes.
  3. Pass the explain-it test for the riskiest part, or rework that part until you do.
  4. Open a small pull request with a human-written note on why the change is right and what was AI-assisted, following your team’s norms.
  5. Finish your log with one paragraph: what you’d do differently next time, and one line to add to your CLAUDE.md or standard brief.

About the Framework

The 4D AI Fluency Framework was created by Rick Dakan and Joseph Feller with Anthropic, and is released under CC BY-NC-SA 4.0. This course’s lessons, examples, and exercises are original.

Where to Go Next