Cursor 2.0 dropped last week, and unlike most recent AI updates, it's actually changed how I work. Two features in particular: Cursor's new Composer model that's 10-50x faster than any other coding model, and parallel agents that finally make running multiple autonomous builds practical. I'll show you Composer building and...
Cloud-based coding agents from Claude Code on the Web, Cursor Cloud Agents, and Codex all promise the same thing: kick off a task, walk away, and come back to a completed pull request. But do they actually deliver? And more importantly, which one fits into your real-world development workflow?
I demonstrate my workflow for running multiple AI coding agents (Claude Sonnet 4.5 and Cursor's Composer 1) in parallel on the same feature, then comparing their work to choose the best implementation. The focus is on solving the practical challenges of reviewing agent work in git worktrees by using a branch-based approach that makes testing, debugging, and merging much more manageable.
Claude Code forgetting things? The key is to manage Claude Code's context window—a.k.a. Context Engineering. This video covers how to be more efficient with your context useage, primarily by marking use of Claude Code's new Subagents feature (game-changer!). You'll also uncover a few hidden gem tips I packed into this one.
Training & community for pro software developers building with AI.
Created by Brian Casel (that's me). I'm a career software developer, founder, and creator of Builder Methods and Agent OS, the system for spec-driven development with AI.
