CompCode Academy

Lesson 41 of 65 · Free to read

Day 41 ΓÇö Reviewing AI-generated code

Month 3 · Week 9 — Quality, Testing, Security & Responsible AI Audience: Final-year students & early-career engineers (0–3 years) Format: Self-paced study + optional live clinic · Suggested time: 4–6 focused hours Key tools: All tools

Overview

Reviewing AI-generated code is literacy: read what you didn’t write. Trust-but-verify with a checklist.

Learning objectives

By the end of this session, you can:

  • Explain the core ideas behind: Reviewing AI-generated code: reading what you didn’t write and the “trust-but-verify” review loop.
  • Apply the ideas using All tools on a realistic task (capstone, internship, or first-job style)
  • Produce the exercise deliverable with clear success criteria
  • Identify common failure modes and how to recover
  • Capture at least one reusable prompt, rule, or checklist for your personal library
  • Decide what must remain human-reviewed for this class of work

Core concepts

Review loop

Skim structure → risk hotspots → tests → dependencies → style/rules compliance → approve or request changes.

Issue log

Every finding becomes training data for rules/prompts.

Tooling for today

Primary tools: All tools. Prefer official docs when APIs change. When a model invents a symbol, verify against source or docs immediately.

Practice posture

You are a final-year or early-career engineer pairing with a very fast teammate (the model): clear intent, grounded context, inspect consequential changes, keep a paper trail (commits, prompts, decisions).

Process diagram

Watch & learn

Study these free videos before or during the exercise. Each embed is chosen to reinforce today's objectives.

Course video

Open on YouTube
Stop Vibe Coding. Use This Instead. — Spec-driven recovery from “accept all” failure modes.

Course video

Open on YouTube
OWASP Top 10: Injection Attacks — Security lens for AI-written handlers and queries.

Worked example / case study

Scenario

Audit Week-8 output against a checklist; log every issue.

Step-by-step

  1. Clarify the outcome in one sentence tied to the exercise below.
  2. Gather grounding context (files, docs, schema, acceptance checks).
  3. Run the primary tool(s): All tools.
  4. Produce the smallest vertical slice that proves the idea.
  5. Verify with a command, test, screenshot, or side-by-side comparison.
  6. Write down one steering note — what you told the AI when it went wrong.

Sample prompt you can adapt

Role: Senior engineer mentoring an early-career developer (pairing with me).
Task: Reviewing AI-generated code: reading what you didn’t write and the “trust-but-verify” review loop.
Context: Final-year / early-career project (capstone, internship, or junior role).
Constraints:
- Match existing project patterns
- No new dependencies unless justified
- Include tests or a verification checklist
- Call out assumptions explicitly
Output: step plan first, then code/files, then verification commands.

Hands-on exercise

Primary task. Audit your Week-8 output against a review checklist and log every issue you find.

Coaching notes

Turn top 3 issues into new Cursor/Claude rules.

Steps

  1. Set up or open the workspace required by: All tools.
  2. Skim today's core concepts and watch the video(s) before prompting.
  3. Execute the task in small commits (or saved artifacts if no-code).
  4. Fill the success checklist below.
  5. Note one surprise and one process improvement for tomorrow.

Success criteria

  • Deliverable matches the exercise description
  • You can explain every AI-generated change in plain language
  • Verification ran (tests, manual check, or published URL)
  • At least one pitfall from this lesson was consciously avoided
  • Artifact saved (repo commit, doc, or published link)

Timebox

Suggested: 90–150 minutes of focused build time after study.

Templates & checklists

AssetPurpose
Prompt stubReuse today's structure (role → task → constraints → format)
Verification checklistTests / manual QA / security skim
Decision logWhat you delegated vs kept human

Copy-paste prompt skeleton

## Goal
Reviewing AI-generated code: reading what you didn’t write and the “trust-but-verify” review loop.

## Context files
- (list paths)

## Constraints
- Stack: (fill)
- Do not: (secrets, drive-by refactors)

## Definition of done
- Audit your Week-8 output against a review checklist and log every issue you find.

Daily reflection (3 minutes)

  • What did AI do well?
  • Where did it confidently fail?
  • What rule will you add to your cookbook/rules file?

Common pitfalls

  • Rubber-stamp because 'tests passed'
  • Only reviewing UI screenshots
  • No written issue log

Key takeaways

  • Reading is the job
  • Checklists catch habitual blind spots
  • Issues feed better rules
  • Tools (All tools) change; the judgment skills transfer.

Resources

  • Official docs for: All tools
  • Course cookbook: keep prompts in a versioned Markdown file in your repo
  • Prior days this week — skim objectives if you skipped ahead

Self-paced lesson — Mastering AI-Assisted Development & Vibe Coding — Day 41 of 65.

New free lessons and course updates. Unsubscribe from any email.