Copilot Cockpit

01 Problem

Powerful AI agents still need memory, boundaries, and review points.

Prompt-by-prompt development makes it difficult to keep priorities, research, execution, and approvals connected. Autonomous loops can also hide too much: what is running, why it was chosen, what it changed, and where a person should intervene.

02 System

A control plane inside the editor where the work already happens.

Copilot Cockpit adds durable planning and execution surfaces to VS Code. The To-Do Cockpit captures and refines work before it is promoted to Ready. Tasks represent focused execution units, Jobs coordinate multi-step workflows, and Research runs benchmark-driven improvement loops. Scheduling, MCP tools, bundled skills, and optional agent support extend the same controlled operating model.

• 01
  Approval firstPlanning artifacts stay separate from executable tasks until the user deliberately promotes them.
• 02
  Different tools for different workTasks, Jobs, and Research remain distinct because one prompt, an ordered workflow, and a benchmark loop have different control needs.
• 03
  Extensible, without hiding controlMCP setup, repo-local skills, scheduling, and optional agents add capability while keeping work visible inside the editor.
• 04
  Stable and Edge channelsA recommended stable VSIX supports normal use while an Edge release exposes the newest changes from the main branch.

03 Role

Product definition shaped through intensive real-world use.

I developed the product model, interaction system, extension architecture, workspace persistence, onboarding, and agent-control concepts while using the tool against active software work. The result reflects a repeated pattern in my projects: make a complex technical process easier to inspect and operate without hiding its important decisions.

04 Evidence

A working extension with a deliberately layered workflow.

The public repository includes the To-Do Cockpit, Tasks, Jobs, Research, workspace settings, onboarding, scheduling, MCP configuration, bundled skills, and optional agent workflows. A concise video shows the extension in motion; the complete feature tour documents how the individual surfaces work together.