ContextQB

@contextqb.com

ContextQB is a field guide for AI-assisted software building. It teaches everyday builders how to brief agents, organize project context, inspect the work, and make the small architectural decisions that keep software coherent. contextqb.com

Another strong metaphor for the agentic operator is a “Context Quarterback” — you manage a team of extraordinary athletes, ensure everyone knows the play, and make sure the ball is delivered to the right place at the right time. To see this metaphor stretched to its breaking point 👀👀 @contextqb.com.

T.W. Simpson@simpsontw.bsky.social · 2w ago

Jazz is a strong metaphor for agentic dev bc it models how I see my role as the operator. I write the shout and suggest a tempo, we play that part together, then the agents break away into solos, improvising within the structure. My role is to hold form, listen, and bring the ensemble back together.

LLMs are marketed as these all-knowing machines. But they are unable to explain *how* they get to a decision and second they cannot know how *you*, as an expert, prefers to decide given a specific context and the organizational commitments you have.

Before you ask an AI agent to build your app, make sure you can explain it to a friend. What happens? Who uses it? Why would they come back? If those answers feel fuzzy, this guide will help you sharpen them. Check out the ContextQB guide to building the mental model of your application 👇

The Mental Model of Your App — ContextQB

Before you write a line of code or prompt a single agent, you have to know — in plain words — what your app is actually for. This guide helps you turn an idea into a working mental model.

contextqb.com

Agentic coding isn't just telling AI what to do. It's deciding what information the agent sees, when it sees it, and what stays in memory long enough to matter. That's what it means to become a Context Quarterback. Read our guide to understanding the context window:

Understanding the Context Window — ContextQB

ContextQB is named for this. The context window is the agent's working memory — finite, lossy, and the most important variable in agentic coding. Understanding how it behaves is the difference between...

contextqb.com

Hello, world 👋 ContextQB is a field guide for building software with AI agents. Still running sprints in our off-season workouts but our MCP works and the playbook is open. And it's free 🤙