Overview

AI, Data Science & Cloud Certificates from Google, IBM & Meta — 50% Off

One plan covers every Professional Certificate on Coursera. 50% off Coursera Plus Annual for 10 days only — price increases June 17.

Unlock All Certificates

Software engineers learn to use Claude across its five working surfaces — claude.ai chat, Projects, Claude Code, Claude Chrome, and Claude Design — to write, review, and maintain production code. The course starts in the browser with chat and shows the three signals that you have outgrown it: copy-paste friction, multi-file change, and long-running tasks. You then move into Claude Code, the terminal agent, where you meet its tool surface (Read, Edit, Bash, Grep) and pin invariants in a project CLAUDE.md so every session starts with the same context. From there you build slash-command skills that wrap Rust binaries like cargo clippy, dispatch sub-agents in parallel with YAML-contract guardrails, and replace raw grep with pmat query enrichment flags (--churn, --faults, --coverage-gaps, -G). The course closes with pmat comply and pmat hooks wired into pre-commit, so failing code cannot land.

Syllabus

Meet Claude

Covers five surfaces — claude.ai chat, Projects, Claude Code, Claude Chrome, Claude Design. Same model reasons across every surface; only the interaction shape changes. A chat turn is prompt in, response out, with a side artifact panel for code the model writes. A Project is a named workspace with pinned reference files so every chat inside it sees the same context.

Claude Code Fundamentals

Covers install — one command puts the claude binary on PATH, no model weights download locally. Authentication trades an API key or console login for a persistent session on first run. Permission modes (default, acceptEdits, bypassPermissions, plan) trade autonomy for safety. claude.ai/code runs the same agent in a browser tab with no local install required, and shared sessions let work started in web continue in terminal and vice versa.

Skills (Slash Commands)

Skills are versioned slash-command files Claude Code recognizes from .claude/commands. Each Markdown file becomes a command — type /name and the agent loads the prompt, then runs it. Frontmatter declares an allowed-tools list and a description; the body uses Bash blocks for read-only inspection and an Instructions section for what to change. Skills make recurring workflows discoverable and reproducible across the team.

Sub-Agents and Reliability

Claude Code's Agent tool spawns a fresh sub-agent in an isolated context to run a focused job, then returns a structured report. Use it to dispatch read-only reviews in parallel against a contract, keeping the main session lean. Sub-agents make complex tasks reliable: divide work, scope tools, then merge findings. This module covers when to delegate, how to write contracts the sub-agents must satisfy, and how parallel review increases coverage without explosion of complexity.

Production Discipline with pmat and Contracts

Production code needs more than agents. This module locks the loop with pmat — a Rust CLI that replaces grep with ranked function queries by Technical Debt Grade, complexity, and coverage — plus contract gates that validate every change and sub-agent output. CLAUDE.md routes the agent to pmat for search, pmat hooks install enforces pre-commit gates, and YAML invariants pin sub-agent shapes. The full claude-from-zero repo demonstrates all four surfaces working as one cycle.

Critical Thinking

Synthesize the full Claude stack — surfaces, tool surface, skills, sub-agents, and pmat contracts — into one repeatable, gated workflow you can take into your own repo.