Skip to content
← Curriculum

Learning module 03 / 06

Blueprints and implementation

Turn scoping into an executable blueprint and deliver verifiable milestones through the six-step cycle.

Learning goal and artifact

A blueprint, an implementation milestone and acceptance evidence

Complete and self-check the connected workshop first, then attempt the extension with fictional or authorized material you select. Reading alone does not establish capability.

Concept summaries

Separate facts, constraints and tasks

CONTEXT records facts, ARCHITECTURE constraints, AGENTS execution rules and CHANGELOG delivered changes. Break work into dependent engineering milestones; each instruction states the task, requirements, constraints and acceptance criteria.

The six-step cycle and controlled recovery

Decompose, dispatch instructions, code, verify, decide the branch and update the blueprint. Skills divide capabilities rather than replacing these steps. Preserve work before comparing repair and rebuild costs; never lower gates to turn a failure into a pass.

Read related topic or next-step material →

Complete small task · free study

Run and repair a verifiable milestone

Fictional client Qinghe Equipment: operators submit fault titles; dispatchers classify and confirm assignments. Lin approves scope, Chen approves data access, and Zhou owns operations. The pilot suggests categories to dispatchers without automatic assignment. Use synthetic tickets, with no client systems or external models.

Follow along: inputs, steps and reasoning

  1. Download ticket-lab.mjs into a dedicated practice folder. Install Node 22+ if needed and confirm with node --version. The file has no dependencies and needs no npm install, keys or network.
  2. Run node ticket-lab.mjs baseline. Among five synthetic cases, the unknown fault is misclassified and an unauthorized request is exposed. Failures exit with code 1. Use CASE lines to locate defects; do not remove tests.
  3. Run node ticket-lab.mjs candidate. Compare repaired rules: reject empty input and secret requests; route unknown categories to human review. This is a deterministic example, not model performance.
  4. Copy it to my-ticket-lab.mjs. Change the baseline unknown fallback to review and reject secret requests before classification. Verify with node my-ticket-lab.mjs baseline. Repair one milestone at a time and preserve failure records.

Worked example

Four-part instruction: implement human review for unknown faults; unknown titles return review; no automatic assignment, network access or secret output; all five cases pass with unauthorized behavior reported separately. Blueprint facts: title input, category or rejected output; constraints: pure function and local synthetic data; M1 validation, M2 classification regression, M3 handover materials.

Try independently first

Independent task: perform both repairs, save 03-blueprint.md and actual terminal output. Document every six-step stage, the diff, PASS/NEEDS_FIX decision and unverified scope. If installation fails, record the error and continue role/scoping work; never claim a successful run.

After answering, reveal reference and common errors

After both repairs, all five cases should pass, SUMMARY failed=0 and exit code 0. Repairing only the unknown fallback leaves the secret case failing, so release remains blocked. Software checks do not establish model reliability, client-data approval or production handover.

Record self-check progress

Stored only in this browser, not independent review approval. Use the downloaded workbook across devices; clearing browser data removes this record.

Extension exercise

Teaching exercise: write requirements, facts and constraints for a fictional ticket classifier. Choose one independently verifiable milestone and issue a four-part instruction. Implement it, record functional, code, architecture and security checks, and explain a PASS or NEEDS_FIX decision and next action.

Use fictional or authorized deidentified material. Keep reports, implementation and checks in your own project; this site accepts no exercise uploads and performs no online grading.

Review criteria

  • Criteria precede implementation; milestones are verifiable and dependencies explicit.
  • Record actual checks and unverified scope; preserve work before recovery decisions.

If criteria are unmet, record gaps and a correction plan, then review again with evidence. Confirm sharing permissions before instructor or peer review.

Complete lessons in this module

Study the full explanations, examples and exercises in these lessons, then integrate the artifacts using the connected workshop above.

  1. Chapter 7: The Six-Step Workflow: The Core Process of AI-Assisted Coding
  2. Chapter 8: The Three Disciplines and One Supplementary Principle
  3. Chapter 9: Inspection-Driven Development: Define Standards Before Letting AI Write Code
  4. Chapter 10: Structural Milestones and Complete Rebuilds
  5. Chapter 11: Requirements Analysis: From Vague to Precise
  6. Chapter 12: Architecture Design: The Art of the Blueprint (CONTEXT.md)
  7. Chapter 13: Effective Constraints: Negative-Space Design and Modular Decoupling
  8. Chapter 14: Context Management: Using /clear and the 'Three-Stage' Rebuild
  9. Chapter 15: The 14-Skill Panorama
  10. Chapter 16: Core and Auxiliary Execution Skills
  11. Chapter 17: Advanced Skills
  12. Chapter 18: Role Locking: Give AI a 'Thinking Hat' in One Sentence
  13. Chapter 19: Separating Research, Planning and Implementation
  14. Chapter 20: Telemetry-Driven Development and Reverse Feeding: Giving AI 'Far-Seeing Eyes'