How I hand off a pull request and stop watching the merge queue
Aaron Quirk on letting an agent take a pull request through a GitHub merge queue: what it fixes when the queue drops it, what it never does, and its limits.
Aaron Quirk ·
Author
Aaron Quirk
CTO
Aaron is CTO at Unstoppable, where he works on the agent workspace and spends most of his time on how coding agents actually behave on real repositories.
What you can do in Unstoppable before signing up
Aaron Quirk on guest chat in the Unstoppable Code web app: what a first-time visitor can ask without an account, how it is paid for, and what signing in adds.
Aaron Quirk ·
Why Choose Unstoppable Code?
AI can generate more code than teams can confidently review. See how Unstoppable Code coordinates coding, verification, and independent review agents.
Aaron Quirk ·
Is Agent Chaos the Reason Your AI Agents Keep Overwriting?
Multi-agent studies reveal serious coordination failures. See how isolated worktrees, shared visibility, and plan reviews reduce agent chaos for teams.
Aaron Quirk ·
What’s New in Agentic AI Development in 2027?
Multi-agent workflows, real cost data, and adoption numbers from 2026. Here's what actually changed in agentic AI development, and what it sets up for 2027.
Aaron Quirk ·
How Do You Actually Run Multiple AI Agents at Once?
Running multiple AI agents used to mean colliding changes. Isolated worktrees let you run several agents in parallel without stepping on each other's code.
Aaron Quirk ·
What are the top 5 Ways to Run Multiple AI Agents at Once
Compare five ways to run multiple AI agents safely, including terminal windows, tmux, manual Git worktrees, and isolated multi-agent workspaces in 2027.
Aaron Quirk ·
Maximizing Pipelines With Your Connected Apps
Connected apps only pay off when something durable chains the calls. How to scope MCP servers, gate writes, and put the sequence in a step that can rerun.
Aaron Quirk ·
What Is an MCP and Why Do Coding Agents Need It?
What is MCP? Learn how the Model Context Protocol lets AI coding agents connect to your tools and data sources through one open, reusable standard in 2027.
Aaron Quirk ·
What Is an AI Agent Skill, and How Does It Help?
What is an AI agent skill? Learn how reusable skills replace repetitive prompts and let coding agents apply the same team knowledge consistently at scale.
Aaron Quirk ·
What Is Agentic AI? What Developers Need to Know in 2027
What is agentic AI? This glossary defines agentic AI, skills, runtimes, orchestration, sandboxes, and every other term development teams need in 2027.
Aaron Quirk ·
How to Set Up Quality Gates for AI-Generated Code
Which checks should gate AI-generated code before it merges?
Aaron Quirk ·
What Is Agentic Development?
Why AI agents differ from autocomplete, and where the field is headed next
Aaron Quirk ·
How to Use Ollama for Private AI-Assisted Development
Run private AI coding agents locally with Ollama
Aaron Quirk ·
How to Orchestrate AI Coding Agents Across Multiple Repos
Run parallel AI agents across multiple repos, safely
Aaron Quirk ·
How to Run Multiple Claude Agents at the Same Time Without Conflicts
Git worktrees isolate agents. Here's how to run several at once
Aaron Quirk ·
How to Use AI Agents Safely on a Production Codebase
AI agents on production code, without the compliance blind spots
Aaron Quirk ·
How to Review an AI Agent's Plan Before It Writes Code
A working rubric for reviewing an AI agent's plan before you approve.
Aaron Quirk ·
How to Supervise AI Coding Agents: Isolation, Plan Review, and Parallel Workflows
Supervise AI coding agents: isolation, plan review, quality gates.
Aaron Quirk ·
How to Manage Parallel Agents Without Losing Track: A Step-by-Step Guide
Step-by-step guide to running parallel coding agents without losing track
Aaron Quirk ·