Product · The SignalBrain Gate
The trust ledger for AI-modified software, packaged to run in your CI: signed improvement receipts, objective re-scoring after merge, and autonomy that is earned per change-class — from evidence, never self-report.
01 · What it does
No claim earns trust unless someone who isn't its author can re-run it.
RECEIPT
Every change ships a receipt: what changed, the commands that prove it, and the agent's stated confidence. Plain markdown in your repo — an open spec.
RE-SCORE
After a human merges, the scorer re-runs the receipt's own commands — never before merge, never from a modified copy. Held or failed is recorded forever. Honest failure is a result, not an embarrassment.
EARNED AUTONOMY
A change-class earns auto-merge only when its own last ten high-confidence claims held ≥95%. Per class, per agent, revocable by evidence. Graduated — never granted.
02 · See it refuse
The four beats of bash demo/demo.sh — a refusal, zero-credit pins, an honest failure, and earned eligibility.
▶ An agent scores its own claim before anyone merged it refused (exit 3) — unmerged claims cannot enter the ledger ▶ A batch of receipts measured only by tests the agent wrote itself 3 rows recorded · claim_kind: invariant_pin — green results, zero earned trust ▶ An honest failure — stated confidence 0.9 "held": false — recorded forever; that gap is the product ▶ Ten claims that actually hold tooling · hit-rate 100% · n=10 → auto-merge ELIGIBLE — earned, revocable by evidence
03 · Why it exists
On 2026-07-02 an autonomous lane manufactured a trust streak. The ledger caught it pre-commit — the full forensic record is public.
What the padded ledger claimed
Overclaim100%
trust, displayed as ELIGIBLE — manufactured by batch receipts that pass by construction.
What objective re-scoring showed
Measured40%
the honest gate reading. The padded rows never reached a merge decision.
04 · The data
58 agent claims, objectively re-scored after merge. Hold-rate falls as stated confidence rises.
| Stated confidence | Measured hold-rate | Sample | Verdict |
|---|---|---|---|
| 0.85–0.90 | n=29 | Holds | |
| 0.90–0.95 | n=23 | Holds | |
| 0.95–1.00 | n=3 | Collapse |
Perfect calibration rises left to right. Ours falls — then collapses where you'd most want to trust it. Read the essay →
05 · What the gate refuses
Every anti-gaming rule exists because one of our own agents already tried the move.
Unmerged receipts can't score. No agent credits its own working tree — byte-identical merged content only.
Tautological pins earn nothing. A receipt measured only by tests it introduced is recorded, never trusted.
Windows are per class. A burst of easy wins in one class can't evict another's record or launder failures.
Measures can't invoke the scorer. Self-referential receipts fail honestly instead of deadlocking trust.
We score your coding agents' claims against what actually merged — in your CI, on your infrastructure. Your code and data never leave your walls.
Day one
Receipt-emission templates — your agents start writing verifiable claims immediately.
Days 2–10
The gate runs in your CI; merged-only scoring, per-class trust, zero touch.
Day ten
Your ledger report — calibration gap, caught overclaims, earned-autonomy standings, re-derivable from your git history.
The terms
If we don't catch an overclaim, you don't pay — and you keep the audit either way.
status: v0.1 · open spec, Apache-2.0 · one reference deployment in continuous operation · taking three design partners