Research

We publish and curate research on agentic coding in enterprise environments. Our focus spans multi-agent orchestration, team adoption patterns, and the evolving best practices that help engineering teams ship faster with AI. Here we share what we learn from training teams and staying close to the cutting edge.

Cursor 2.4: Subagents, Skills, and What They Mean for Your Workflow
3 min read

Cursor 2.4: Subagents, Skills, and What They Mean for Your Workflow

Cursor 2.4 introduces subagents, skills, and image generation. Here's how these features fit into a structured AI development workflow.

January 28, 2026·Rogier Muller
Cursor Gas Town: Multi-Agent Orchestration for Cursor CLI
6 min read

Cursor Gas Town: Multi-Agent Orchestration for Cursor CLI

We built Cursor Gas Town—a Cursor CLI implementation of Steve Yegge's Gas Town multi-agent orchestrator. Built in collaboration with the Cursor engineering team, it brings persistent work tracking and multi-agent coordination to Cursor workflows.

January 28, 2026·Rogier Muller
Designing Codebases for AI Agents: Peter Steinberger's Approach
4 min read

Designing Codebases for AI Agents: Peter Steinberger's Approach

Peter Steinberger doesn't design codebases for himself anymore—he engineers them so AI agents can work efficiently. Here's how to structure code for maximum agent productivity.

January 28, 2026·Rogier Muller
Gas Town: Steve Yegge's Multi-Agent Orchestrator and What It Means for AI Development
4 min read

Gas Town: Steve Yegge's Multi-Agent Orchestrator and What It Means for AI Development

Steve Yegge's Gas Town runs 20-30 Claude Code agents in parallel. Here's how multi-agent orchestration is changing AI-assisted development and why workflow durability matters.

January 28, 2026·Rogier Muller
Job vs Gym: Which Skills Should You Protect from AI?
4 min read

Job vs Gym: Which Skills Should You Protect from AI?

Daniel Miessler's Job vs Gym framework helps developers decide when to use AI and when to do the work themselves. Here's how to maintain the skills that matter while leveraging AI for everything else.

January 28, 2026·Rogier Muller
Why Senior Engineers Accept More AI Suggestions Than Juniors
5 min read

Why Senior Engineers Accept More AI Suggestions Than Juniors

New research shows senior engineers accept 22% more AI suggestions than juniors. AI coding tools amplify existing engineering skill, not replace it. Here's what this means for teams.

January 28, 2026·Rogier Muller
How Y Combinator Founders Actually Ship with AI Coding Tools
4 min read

How Y Combinator Founders Actually Ship with AI Coding Tools

Y Combinator asked their founders about AI coding patterns. One insight stood out: when AI produces garbage, git reset --hard and implement clean. Stop stacking fix attempts.

January 28, 2026·Rogier Muller