Lesson 28 of 65 · Free to read
Day 28 ΓÇö Autonomous multi-file features and iterative self-correction.
Month 2 · Week 6 — Claude Code & Agentic CLI Coding 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: Claude Code
Overview
Autonomous multi-file features succeed when you review diffs tightly and request changes in natural language until correct.
Learning objectives
By the end of this session, you can:
- Explain the core ideas behind: Autonomous multi-file features and iterative self-correction.
- Apply the ideas using Claude Code 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
Diff review checklist
Correctness, security, compatibility, tests, scope creep.
Steering language
“Keep public API stable”, “move this to existing util”, “add negative test for X”.
Tooling for today
Primary tools: Claude Code. 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
Course video
Worked example / case study
Scenario
Delegate a feature; review; request changes; accept final result.
Step-by-step
- Clarify the outcome in one sentence tied to the exercise below.
- Gather grounding context (files, docs, schema, acceptance checks).
- Run the primary tool(s): Claude Code.
- Produce the smallest vertical slice that proves the idea.
- Verify with a command, test, screenshot, or side-by-side comparison.
- 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: Autonomous multi-file features and iterative self-correction.
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. Delegate a feature, review the diff, request changes in natural language, and accept the final result.
Coaching notes
Track number of steering iterations — aim to improve briefing next time.
Steps
- Set up or open the workspace required by: Claude Code.
- Skim today's core concepts and watch the video(s) before prompting.
- Execute the task in small commits (or saved artifacts if no-code).
- Fill the success checklist below.
- 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
| Asset | Purpose |
|---|---|
| Prompt stub | Reuse today's structure (role → task → constraints → format) |
| Verification checklist | Tests / manual QA / security skim |
| Decision log | What you delegated vs kept human |
Copy-paste prompt skeleton
## Goal
Autonomous multi-file features and iterative self-correction.
## Context files
- (list paths)
## Constraints
- Stack: (fill)
- Do not: (secrets, drive-by refactors)
## Definition of done
- Delegate a feature, review the diff, request changes in natural language, and accept the final result.
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
- LGTM on 800-line diffs
- Arguing with the agent instead of tightening constraints
- Leaving dead code from partial attempts
Key takeaways
- Steering is the skill
- Checklists beat vibes on big diffs
- Iteration count informs better briefs
- Tools (Claude Code) change; the judgment skills transfer.
Resources
- Official docs for: Claude Code
- 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 28 of 65.