Failed runs are free
A run that misses its frozen Definition of Good is not billable. The failure still lands on a receipt; you just do not pay. Why we wired billing this way.
the ledger
previous entries
page 03 / 03The win ledger: what we learn when the blinds come off
Judges stay blind during a run for fairness. After it closes, an outcome survey unblinds every role, and results accumulate into the win ledger: a per-engine, per-provider, per-model strength record that guides future roster choices.
The integrator: one final from many candidates
After judging, an integrator builds one complete final from the winning candidate plus approved grafts from the others, then re-runs the gate. You merge one thing, not a pile.
Headers first: docs that agents can route
Give every document a structured header (description, status, tags) and make agents read headers before bodies. Relevance gets decided in 60 words instead of full files, and superseded docs announce themselves before anyone acts on them.
Why a split verdict is a feature
When judges disagree, Fusion records the split and preserves the dissent instead of averaging it away. A 2–1 verdict tells you exactly where the risk lives.
Answer first: how we write everything
We write answer first: every entry states its verdict in the opening paragraphs and in a frontmatter field, because readers and answer engines both quote the top. The mechanism follows for anyone who wants proof.
Blind judging: what the jury sees, and what it can't
Fusion judges never learn which agent wrote which candidate. Packets are stripped of identity and independently randomized per judge, so verdicts attach to the work, not the brand.
Verified fails closed
Verified is a narrow, earned state: the frozen Definition of Good was met and the evidence exists. If a hard criterion, required gate, or required evidence is missing or unparseable, the run is not Verified. Ambiguity resolves against us; waivers stay visible on the Receipt.
The Definition of Good: criteria a machine can grade
A Definition of Good is the frozen, testable contract a run must meet: hard criteria that can fail the run, soft criteria that shape it, and a gate a machine can execute.
Why this blog is MDX in a repo
Posts are MDX files committed to the repo, reviewed in pull requests, and served as static HTML. The frontmatter mirrors a future CMS collection, so migrating later is an import script, not a rewrite.
One task, rival agents, parallel lanes
Fusion runs the same task through competing coding agents in parallel lanes, then keeps only what survives judging. Competition is the quality mechanism, not a gimmick.
Trust is the bottleneck now
AI made code cheap to produce and expensive to trust. The fix is not a better generator; it is a verification layer that proves what survived.