Ship with the process attached.
Bugs reproduce before they get fixed, tests go red before green, releases wait for your approval. Describe that once and every task your team or its agents pick up runs the same way, from the client each person already codes in.
what monday looks like
- 01Connect your client and install Bug Fix and Feature from the catalog
- 02File one real bug. Watch the workflow attach itself and hand your agent step one
- 03Sit at the approval gate: the release waits until you say go
- 04Edit one step instruction. The next run inherits it, and nobody reads a memo
The bug-fix loop, as it runs
A bug arrives
Typed, fired from your stack, or found by another workflow.
Reproduce
No fix before the failure is real and captured.
Branch on reality
Can’t reproduce? It closes with an explanation instead of rotting.
Failing test, then the fix
Red before green. The fix ships with proof.
You approve the release
The gate holds until a human says go.
Release
Logged, attributed, done.
install these
questions
Does this replace our issue tracker?
It becomes the system of record for AI-driven work: tasks with hierarchy, workflows, and a full query surface your agents reach over MCP. Whether it replaces or sits beside your tracker is your call; nothing forces a migration to start.
Which coding clients work?
Claude Code, Cursor, ChatGPT, and any client that speaks MCP. The engine hands out steps; whichever client is connected does the work.
Can an agent skip the process when nobody is looking?
Routing attaches the workflow at task creation, and gates are evaluated by the engine on every advance. A run that has not satisfied a gate does not move, whoever or whatever is driving.
Can implementation run on our own machines?
Yes. Attended runs already execute in your local client. For unattended work, a custom runner on your infra receives an envelope and a lease, or you point dispatch at your own OpenCode server.