Wirewalk Instituteof AI
ven-190 Intermediate Waitlist

AI Coding Assistants: Copilot, Claude Code, Cursor and Codex

For software engineers and engineering leads who want to get real productivity from AI coding assistants and agents without shipping unreviewed, insecure or unmaintainable code.

The curriculum is being prepared and reviewed. Enrollment is not open yet.

About this course

AI coding tools have converged on a similar feature set (inline completions, chat, agents that edit many files and run commands, cloud agents that turn issues into pull requests, automated code review and MCP integrations), yet they differ sharply in where they live and how they fit a team: an extension across many IDEs, a terminal-first agent, an AI-native editor, or a CLI and cloud service tied to a chat subscription. This course teaches each tool hands-on and then teaches the durable skill underneath all of them: giving an agent the right context, constraining what it may do, and verifying what it produces.

You will configure GitHub Copilot agent mode, Copilot cloud agent (formerly the Copilot coding agent) and Copilot code review; Claude Code's CLAUDE.md, permission modes, plan mode, hooks, skills, subagents and MCP servers; Codex's AGENTS.md, sandboxing and approval modes across CLI, IDE and cloud tasks; and Cursor's Agent, Tab, rules, cloud agents and Bugbot. The later modules cover test-first loops, reviewing AI-written diffs for hallucinated APIs and silent behavior changes, secrets and prompt injection through repositories and issues, licensing and data-retention settings, and measuring impact honestly. Product details are stated as of the review month with links to each vendor's documentation. Completion and a passing exam score earn a Wirewalk Institute of AI certificate of completion and assessment; it is not a vendor certification and is not endorsed by any vendor named.

What you will be able to do

  • Compare Copilot, Claude Code, Cursor and Codex on surface, agent capabilities, model access and pricing model, and match a tool to a team's workflow
  • Configure instruction files, permission and approval modes, and MCP servers so an agent has the context and limits a task needs
  • Delegate an issue to a cloud coding agent and review the resulting pull request to a merge-ready standard
  • Run test-first agent loops in which the agent executes tests, linters and type checkers before proposing changes
  • Identify hallucinated APIs, silent behavior changes and security regressions in AI-written diffs
  • Mitigate secrets exposure and prompt injection through repositories, issues and tool output in agentic workflows
  • Plan a team rollout with organization policies, data-retention and code-referencing settings, and honest impact metrics

Syllabus

6 modules · 17 lessons · about 14 hours

Module 1: The Coding Assistant Landscape

How completions, chat, local agents and cloud agents differ, and how the four tools are positioned.
3 lessons
  1. From Autocomplete to Cloud Agents: Completions, Chat, Agent Mode and Background Work
  2. Copilot, Claude Code, Cursor and Codex: Surfaces, Model Access and Pricing Models
  3. Choosing by Workflow: IDE-Centric, Terminal-Centric and Pull-Request-Centric Teams

Module 2: GitHub Copilot

Copilot across editors and on GitHub itself, from next edit suggestions to issue-to-PR agents.
3 lessons
  1. Copilot in VS Code and JetBrains: Next Edit Suggestions, Chat and Agent Mode
  2. Copilot Cloud Agent: Assigning Issues and Reviewing Its Pull Requests
  3. Copilot Code Review, Custom Instructions and Organization Policies

Module 3: Claude Code and Codex

Two terminal-first agents and their configuration, extension and safety controls.
3 lessons
  1. Claude Code in the Terminal and IDE: CLAUDE.md, Permission Modes and Plan Mode
  2. Extending Claude Code: Hooks, Skills, Subagents and MCP Servers
  3. Codex CLI, IDE Extension and Cloud Tasks: AGENTS.md, Sandboxing and Approval Modes

Module 4: Cursor

The AI-native editor's agent, completions, project rules and automated review.
2 lessons
  1. Cursor Agent, Tab and Plan Mode for Multi-File Changes
  2. Project Rules, Cloud Agents and Bugbot for Pull Request Review

Module 5: Working Effectively with Coding Agents

The tool-independent practices that decide whether agent output is usable.
3 lessons
  1. Context Engineering for Codebases: Instruction Files, Specs and Right-Sized Tasks
  2. Test-First Loops: Letting Agents Run Tests, Linters and Type Checkers
  3. Reviewing AI-Written Code: Hallucinated APIs, Silent Behavior Changes and Over-Engineering

Module 6: Security and Team Rollout

Protecting secrets and systems, managing licensing and data settings, and measuring impact.
3 lessons
  1. Secrets, Sandboxes and Prompt Injection Through Repositories, Issues and Tool Output
  2. Code Referencing, Licensing and Data-Retention Settings by Tool
  3. Measuring Impact Honestly: Cycle Time, Rework, Defects and Developer Experience

Exam and certificate

The exam unlocks once you have completed every lesson. It draws 20 questions from a larger bank, spread across the modules, with the answer options shuffled for each attempt. You have 40 minutes and need 80% to pass. After a failed attempt you can try again after 24 hours, up to 3 attempts in total. Feedback is given per module, never as the answer key.

Passing earns a certificate of completion and assessment from the Wirewalk Institute of AI with a unique ID that anyone can check at institute.wirewalk.com/verify. It is not an accredited qualification or a vendor certification. How certification works.

The Wirewalk Institute of AI is independent. This course teaches publicly documented products and is not affiliated with or endorsed by GitHub (Microsoft), Anthropic, Cursor (Anysphere), or OpenAI. Product and company names are trademarks of their respective owners.

More in AI Models and Vendors

All 22 courses in this track
ven-001 Free intro Available

Your First Hour with ChatGPT, Claude and Gemini

A hands-on hour with ChatGPT, Claude and Gemini, told through one small business racing a deadline. Set up an account with a privacy setting you chose, decide what never goes into a personal account, write prompts that produce usable drafts, use files and web search, catch confident mistakes before they go out, and pick the assistant that fits how you work.

1 h · 7 lessons Free intro
ven-110 Basic Available

ChatGPT and the OpenAI Platform for Professionals

A practical, current tour of ChatGPT as a professional tool: choosing a plan and model, prompting well, analyzing files, researching with citations, using images and voice, organizing work in projects and memory, connecting apps and plugins, delegating multi-step work to ChatGPT Work, and knowing which admin and privacy controls matter. Ends with clear guidance on moving a workflow to the OpenAI API.

8 h · 15 lessons See price at checkout
ven-120 Basic Available

Claude for Professionals

Learn Claude by solving one firm's real problem: getting through renewal season with too few analysts and without putting client data in the wrong place. Each module compares the approaches professionals actually choose between, shows a realistic failure and its fix, and ends with a Decision Lab where you make the call under pressure.

12 h · 15 lessons See price at checkout