AI / FIELD 04

Brief the work.
Build carefully.
Verify the result.

Learn what AI can do, give Claude Code or Codex a bounded task, and inspect the evidence before you call it finished.

Paper task brief connected to a blue project folder and an inspection loupe
Original conceptual illustration · not product UI or execution evidence.

CLAUDE CODE

Start with inspection.

Open your first project ↗Write CLAUDE.md ↗

01 / LEARNING STAGE

Beginner

Understand the boundary between a suggestion, an action, and evidence.

AI-0001Generative AI: Models, Chatbots, Agents, and Tools

Separate a generated suggestion from a tool action, then turn a small contact-form request into something you can inspect and verify.

AI-0002Write an AI Task Brief with Clear Acceptance Criteria

Replace “improve this form” with a bounded goal, relevant context, allowed files, acceptance checks, and explicit reasons to stop and ask.

AI-0003Tokens, Context, and Memory: What an Agent Can Use

Build a compact project handoff without confusing the current context, durable instructions, model training, and a summary of earlier work.

AI-0004Verify AI Output and Protect Project Data

Use a claim ledger and a data boundary to decide what can be checked locally, what may be shared, and which actions require a separate approval.

02 / LEARNING STAGE

Builder

Open a project, record its rules, and make one bounded change.

AI-0005Your First Read-Only Project in Claude Code

Choose the current official setup for your environment, open a disposable project, and verify a read-only contact-form inspection before allowing edits.

AI-0006Write a CLAUDE.md That Describes Your Actual Project

Turn verified project facts into concise Claude Code instructions, keeping durable rules separate from one-off tasks and permission enforcement.

AI-0007Claude Code: Plan, Build, Then Review a Small Change

Improve one contact-form behavior with a scoped plan, a failing acceptance check, a small patch, and an independent review of the resulting diff.

AI-0009Your First Read-Only Project in Codex

Identify your current Codex environment, inspect a disposable repository, and verify the returned file inventory before authorizing a modification.

AI-0010Write AGENTS.md with Clear Directory Boundaries

Describe verified project facts, commands, and approval boundaries for Codex, then check how root and nested guidance apply to the next task.

03 / LEARNING STAGE

Operator

Choose environments and extensions without granting unnecessary access.

AI-0008Claude Code Extensions: Skills, Hooks, Subagents, and MCP

Choose the smallest extension for a repeatable workflow, and identify what it can read, execute, or send before adding it to a project.

AI-0011Codex Local, Worktree, or Cloud: Choose the Right Boundary

Separate working-file isolation from security and hosted execution, then choose a workspace with an explicit plan for setup, review, and cleanup.

AI-0012Codex Skills, MCP, Subagents, and Scheduled Tasks

Choose reusable guidance, a connector, bounded delegation, or a scheduled check based on the task’s real need and the access each option requires.

04 / LEARNING STAGE

Expert practice

Coordinate work, transfer evidence, and review the integrated result. A practice stage, not a credential.

AI-0013Hand Off Work Between Claude Code and Codex

Transfer a bounded project state with files, evidence, limitations, and a next action instead of assuming two agents share conversation history.

AI-0014Coordinate Parallel AI Agents Without File Collisions

Split independent work with named file owners, dependency gates, a shared budget, and an integration review that catches cross-task assumptions.

AI-0015Test and Review AI-Generated Code Beyond “Tests Pass”

Combine a regression check, diff inspection, browser behavior, and explicit limits so a passing command cannot hide an incomplete contact-form change.

TWO LOCAL INSTRUMENTS

Make the brief tangible.

Deterministic Markdown templates. No model calls, account connection, or input storage.

Loose paper notes organized into a structured brief with cobalt and lime tabs
AI-T01

AI Task Brief Builder

Turn your goal, scope, and acceptance criteria into a clear Markdown task brief locally in your browser.

One project folder branching into two paper instruction booklets
AI-T02

Agent Instructions Builder

Draft AGENTS.md or CLAUDE.md from the project facts and boundaries you supply, without inventing commands.