What it is

A coding-agent session is an artifact: what the user asked, what the agent read, what it changed, what it claimed. Parallax records it (no extra tokens: it reads what the agent already wrote), and when the session ends it asks the Conifer router which models from other labs are best for that exact task. Those models re-do the important part blind, hunt for bugs, security holes, dead code and slower-than-needed code, and every finding is run in a throwaway copy of your repo. Nothing reaches you as an opinion.

What “proven” means#

A bug is real only if the reviewer writes a test that fails on your current code and passes with its fix, and your whole suite still passes. A faster rewrite counts only if the sandbox measures it faster and the suite still passes. Dead code counts only if removing it leaves the suite green. A reviewer that tells a convincing story and cannot write the failing test gets nothing.

What you get#

A pull request per proven mechanism, with the fix and the proving test, against your base branch. On GitHub, a check on every PR with proven findings as line annotations. A memory: a lesson from every proven finding, injected into the next session that touches that file, so the same defect is not written twice. And a scoreboard: which model is right on which kind of task, on your code, with the cost attached.

Why other labs#

A model is bad at catching the kinds of bugs it tends to write. Reviewers are always from labs other than the one that did the work, picked per task by the router, bounded to the Pareto frontier: a seat is used only if nothing ranked above it is cheaper, and “cheaper” is what it actually cost you per call once measured.