Skip to content
Start a project
Tandem · Agent orchestration · Our own product

Hand off the work. Keep the decisions.

We built Tandem to queue coding agents on the right machine, ask the decisions that need a person, and hand back work ready to review.

At a glance

3native apps
~3wkfirst commit to live
2runner platforms
1shared backend

01 · Problem

AI agents are fast, but someone still has to babysit them.

Work we meant to hand off still tied us to a desk.

Why it hurts

Agents stop to ask a question with nobody there, run only on the machine in front of us, and forget how we like things done. Finished work gets scattered across terminals.

02 · User

A builder working across Mac and Windows
  • Answer agents from the phone
  • One list of what's running
  • Never miss a hard-to-undo call

03 · Flows

  1. QueueTask, agent, machine
  2. Pick upThe right runner starts
  3. WorkClaude or Codex
  4. DecideA person, or Autopilot
  5. ReviewCheck the returned work
  6. ShipPR or files + report

04 · Wireframes

3 screens
Task list
Decision
Review

Flow sketches reconstructed for this case study.

Why the decision stands out

The flow gives decisions their own step. Routine choices can settle through Autopilot or a timed proposal; anything hard to undo always waits for a person.

05 · Design system

Palette study
Canvas
Ink
Claude
Running
Stop

Illustrative colours; native type follows each platform.

SF Pro · Segoe UI VariableMac + iPhone: SF Pro, SF MonoWindows: Segoe UI Variable, Cascadia Mono

06 · Final

Tandem Mac agent controls with run controls
Mac · agent controls
Tandem on iPhone showing its own running task
iPhone · running task

07 · Results

Agents can work across
Mac + Windows
Queue, decide and review from
iPhone
Hard-to-undo actions
Wait for us
How we measured

As of 15 November 2026, native iPhone, Mac and Windows apps share one backend. The first commit was 26 October. Agents were observed running on Mac and Windows at the same time in one snapshot. We have not measured human time saved.

08 · GitHub

Tandem

Source code is private. We can discuss the approach on a call.

Private repository