Turn Linear issues into pull requests with local agents
Switchboard connects issue triage to agent execution so clear Linear work can become reviewable branches and pull requests without hiding the work in a separate queue.
Best for
Teams that want controlled agent automation from Linear.
Why Junction
Switchboard is for targeted automation: clear issues, reviewable branches, visible state, and humans still deciding what lands.
What it means
Junction is the local-first control plane for AI coding agents.
Start from issues that are ready for agents
Switchboard works best when Linear issues include acceptance criteria, scope boundaries, and enough repository context for a local agent to start safely.
Route work intentionally
Not every issue belongs on automation. Switchboard gives teams room to decide which projects, labels, and states should become agent work.
End with something reviewable
The goal is not hidden background work. The goal is a branch, a pull request, and enough context for a human reviewer to decide what happens next.
Field notes
Related Junction guides
How Switchboard Turns Linear Issues Into Pull Requests
See how Junction's Switchboard watches Linear, spawns isolated worktrees, runs agents, and opens pull requests when the work is done.
Write Linear Issues Ready for AI Agent Automation
Learn how to scope Linear issues so Switchboard can turn clear, bounded work into reviewable AI agent pull requests.
Configure Switchboard Route Settings for Team and Repo Routing
Learn how Switchboard route settings map Linear teams and repositories to daemons, agents, models, branches, and automation rules.
Get started
Keep agent work visible from anywhere.
Install the daemon where your projects already run, connect Junction, and use one browser workspace for active AI coding agents.