Skip to content

Lift 1: Gear Check — The Director's Toolkit

Why a Gear Check?

You check your gear before you drop into a line — not because you don't know how to ski, but because starting on the same page matters more than starting fast.

This lift is a rapid recap of the foundational concepts from the Blue Square track: context engineering, skills, delegation patterns, and the Explore → Plan → Implement → Verify workflow. If you've been building with AI coding assistants, most of this will feel familiar. If some of it's new, that's fine — lean on your teammates. If you already know it, help your teammates get there. Teaching deepens your own understanding.

The goal isn't to test anyone. It's to get your team to a shared starting point — same vocabulary, same frameworks, same toolkit — so that when Lift 2 introduces evals and measurement, you're all working from the same foundation.

We also cover deployment in Coder, which is new for everyone regardless of experience.

What You'll Learn

  • What the pre-configured deployment pipeline gives you and why deploying early matters
  • How context engineering scales from a single file to a layered architecture with path-scoped rules
  • How skills turn role gaps into specialized AI roles — and why the refinement loop matters more than the file
  • How specs and acceptance criteria become delegation contracts for parallel workstreams — and what breaks when you scale

Sections

  1. Deployment in Coder — What you get for free and why you deploy before you build
  2. Context Engineering — From a context file to a layered architecture
  3. Skills as Specialized Roles — Encoding judgment into reusable, shareable AI roles
  4. Delegation & Parallelization — Contracts, parallel execution, and the visibility problem

By the End of This Lift

  • Your application is deployed to a live URL before you write your first feature
  • You understand the layered context hierarchy and when to use path-scoped rules vs. project-level context
  • You can identify role gaps on your team and frame them as skill candidates
  • You know how to structure parallel workstreams with specs as contracts — and you can see the problem that creates at scale
  • Your team shares a common vocabulary: Three Pillars, delegation contracts, Explore → Plan → Implement → Verify, the oxygen tank, the delegation-ready test