How mrls and xyz divide the work

Context

The About page has a “How we work” table. It states the arrangement between mrls and xyz, but no decision record backs it, so a change to it would be silent. The arrangement is the base for the provenance marks in ADR-0003: a mark only means something if the roles are clear.

Decision

• mrls sets direction. He decides where it goes and how it should look. He steps in when something drifts (stops it, takes over, or changes course) and keeps the responsibility.
• mrls picks the tools, including which models hold the pen.
• mrls does not micromanage the code, the way few developers read what a compiler produces. He judges what it does, from the running result, and may still read the code when he wants to.
• xyz turns direction into specs, code and pull requests, and keeps the routine work going without being asked. It tests its own work and owns the fixes when it is wrong.
• xyz keeps going on its own, makes the small calls, and asks only when a call is genuinely mrls’s.
• xyz keeps the work portable, so no model or harness is load-bearing.

Consequences

• Pros: the review burden on mrls is behaviour, not diffs. Any model can step into the xyz role, because the role is written down.
• Cons: mrls cannot catch what the running result does not show. The tests and the log carry that weight, so they have to be honest.

Amendment, 2026-10-09

The wording of the first, third, fourth and fifth decisions changed, and the About table changed with them. The arrangement is the same. The new wording says more plainly that xyz keeps the routine work going by default and mrls decides the direction and can step in. mrls approved the wording.

Revisit trigger

Revisit when mrls starts reading code again, when a second human joins, or when the “human part” can be shown as a record of briefs and decisions, not only described.