How a writing run in muxcode plans a change, builds it and proves it, and why a model's yes is never enough to pass the work.
A writing run plans first, builds second and proves it last, one route at a time. A small change your checks can prove runs solo instead.
The gate is the host's own code. It checks scope, exit codes, secrets and project checks before any judge, and costs no tokens.
Clef answers with a probability, and the host acts only when it clears a fixed bar, such as 0.6, 0.7, 0.8 or 0.85. It no longer picks a seat's effort or worker.
Cowork in mux on the web now starts from a shelf of ready-made coworkers, opens with what your coworkers finished by themselves, and lets a coworker keep files and build an app that only you can preview. Here is what each part does, what mux's code decides rather than a model, and where the limits are.
A language model does not fail like normal software. It writes a fluent, confident review that may be wrong, and one good review tells you nothing about the next hundred. So every change to Reviewer, the Cowork coworker that reviews pull requests, runs through the same eval before it ships. This is what an eval is, why Reviewer has one, and what the second round found on 7 November 2026, with the code index's own code in place of a simulation and 30 new cases.
Most bugs that reach production pass review because the reviewer only saw the change. Reviewer, Cowork's ready-made coworker for pull requests, reads the callers the change reaches before it writes a word. On a 24-case eval it found the broken caller in every cross-file run, against none without it, and left every correct change alone. Here is how it works, why a pull request cannot steer it, and how we know.
We pressed Start on a real bug report. mux wrote a failing test, fixed the bug, checked both and opened a draft pull request 91 minutes later. Here is every step, how long it took, the five mistakes the run showed us in Cowork, and how each is now fixed.
How a team's agents share what they learn in Git, find code through one call, and reach both over MCP, with the limits, the plans and the off switches.
When a task fills its context window, pi opens a fresh one with a short handoff instead of a summary; here is where that line sits, what crosses it and what it costs.
A model in a loop can ask for anything, and the code around it decides what happens. Why that code should be yours, and what muxcode already gives you.
A tour of muxcode and mux, end to end: what runs on your Mac, the route one change takes, the gate, signing in, the code index, the sandbox, the plans, and how to turn each hosted part off.
A model can pass a physics exam and still break in a loop that nobody reads. muxcode puts code around the model, so each change is checked before it reaches you.