📖Lessons
The Agentic Coding Revolution
How AI coding tools evolved from autocomplete to autonomous agents that write, test, and debug code
Kiro: Spec-Driven Development
Master Kiro's unique approach — specs, steering, hooks, and autopilot for structured AI development
Claude Code: Terminal-Native Agent
Master Claude Code's terminal-first approach — from CLAUDE.md and slash commands to hooks, subagents, headless mode, and CI integration
Cursor: The AI-First IDE
Master Cursor's agent mode, background agents, Cursor Rules, Composer, and the workflows that make it a developer favorite
Copilot, Windsurf & the IDE Landscape
Compare GitHub Copilot's agentic evolution, Windsurf's Cascade, and choose the right tool for your workflow
Agentic Coding Best Practices
Maximize productivity with effective prompting, review workflows, and avoiding common pitfalls
🎯Missions
M-084Build a SCOPE Prompt Optimizer
Nebula Corp's developers are writing vague prompts for their agentic coding tools, leading to poor results. Build a prompt optimizer that takes a vague prompt and enhances it using the SCOPE framework: Specific (what exactly?), Context (which files/systems?), Outcome (what should the result look like?), Patterns (what conventions?), Edge cases (what to handle?). The optimizer should analyze the input prompt and return an enhanced version with all SCOPE elements.
M-082Build Your First Agentic Code Reviewer
Nebula Corp wants an automated code review assistant that analyzes code snippets for common issues. Build a simple rule-based code reviewer that checks for common problems: console.log statements left in production code, TODO comments, functions that are too long, and missing error handling. The reviewer should return a structured list of findings with severity levels.
M-083Design a Spec-Driven Feature Plan
Nebula Corp wants to add a 'favorites' feature to their app. Instead of jumping straight to code, practice the spec-driven approach: write structured requirements with user stories and acceptance criteria, then break them into ordered implementation tasks. The function should take a feature description and return a structured spec object with requirements and tasks.
🔧Workshops
W-023Build a CLI App with Claude Code
Use Claude Code to build a Node.js CLI tool from scratch — entirely from the terminal. Set up CLAUDE.md for project context, create custom slash commands for your workflow, use parameterized commands, configure hooks for auto-linting, and leverage subagents for parallel tasks. By the end, you'll have a working CLI and a Claude Code setup you can reuse on any project.
W-025Build a Full-Stack Feature with Cursor
Use Cursor to build a complete full-stack feature in a Next.js app — from database schema to UI. Set up Cursor Rules for team conventions, use Agent Mode for autonomous multi-file changes, leverage the @-mention system for precise context, and spawn a background agent for a parallel task. Learn the Cursor-specific workflows that make it a developer favorite.
W-026Multi-Tool Agentic Workflow
Set up a professional development workflow that combines multiple agentic coding tools. Configure Claude Code for CI automation and terminal tasks, Cursor Rules for team-wide IDE conventions, and Kiro steering for spec-driven features. Build a shared convention system that works across all tools, and set up automated code review with Claude Code in GitHub Actions.
W-024Spec-Driven Development with Kiro
Use Kiro's spec-driven workflow to plan and build a feature from requirements to working code. Create structured specs with user stories and acceptance criteria, set up steering files for team conventions, build hooks for automated workflows, and use autopilot mode for implementation. Experience the difference between vibe coding and spec-driven development.