CompCode Academy

Lesson 16 of 65 · Free to read

Day 16 ΓÇö Context windows and information architecture

Month 1 · Week 4 — Context Engineering 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, GitHub Copilot

Overview

Context engineering is information architecture for models: what to include, exclude, and order so the first attempt is mostly right.

Learning objectives

By the end of this session, you can:

  • Explain the core ideas behind: Context windows and information architecture: what to include, exclude, and order.
  • Apply the ideas using Claude, GitHub Copilot 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

Bundle order that works

Rules/style → types/schemas → target files → exemplar patterns → tests → task.

Exclusion list

node_modules, build outputs, secrets, huge lockfiles, unrelated apps in a monorepo.

Tooling for today

Primary tools: Claude, GitHub Copilot. 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
Deep Dive into LLMs like ChatGPT (Andrej Karpathy) — Training, model “psychology,” and practical use.

Course video

Open on YouTube
Cursor AI Tutorial for Beginners (Volo Builds) — Inline, chat, Composer, and troubleshooting with AI.

Worked example / case study

Scenario

Assemble a context bundle that lets the AI add a feature correctly on the first try.

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): Claude, GitHub Copilot.
  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: Context windows and information architecture: what to include, exclude, and order.
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. Take a multi-file repo and assemble a context bundle that lets the AI add a feature correctly on the first try.

Coaching notes

Measure: tokens roughly, and whether attempt #1 compiled.

Steps

  1. Set up or open the workspace required by: Claude, GitHub Copilot.
  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
Context windows and information architecture: what to include, exclude, and order.

## Context files
- (list paths)

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

## Definition of done
- Take a multi-file repo and assemble a context bundle that lets the AI add a feature correctly on the first try.

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

  • Dumping the whole repo
  • Putting the task text before critical types
  • Omitting the exemplar pattern file

Key takeaways

  • Order is a prompt feature
  • Exclusion is as important as inclusion
  • First-try success is a design goal
  • Tools (Claude, GitHub Copilot) change; the judgment skills transfer.

Resources

  • Official docs for: Claude, GitHub Copilot
  • 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 16 of 65.

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