Skip to main content
Most AI review is two stages: the model emits text, and the text becomes a comment. There is nothing between the model’s judgment and your PR thread. That is why single-stage reviewers are confidently wrong — a hallucinated finding has nothing to clear before it reaches you. Sigilix puts five gates in that gap. A finding produced by a specialist is not a comment; it is a candidate. To become a posted finding, it has to survive evidence, provenance contracts, refute/execute, proof-tier receipts, and memory. Believability here is architectural, not a prompt that says “please be accurate.”

​
The five gates

1

Evidence

A finding has to point at something. It must cite the code it is about — the lines it quotes, the symbol it names. A finding with no anchor to real code does not clear this gate.
2

Provenance contracts

The cited evidence has to actually correspond to the diff under review. The finding’s claim is checked against where it says it came from — the right file, the right lines, the change actually present. This is what stops a finding from being attached to code that does not exist or to a line it never touched.
3

Refute / execute

Sigilix actively tries to disprove the finding. The synthesizer cross-references the claim against the surrounding source and the repo context; where a claim is checkable by execution, it is checked. A claim that survives the attempt to refute it is far stronger than one that was simply asserted.
4

Proof-tier receipts

A finding that survives is stamped with a receipt that records how it earned its place — see the tiers below. The receipt travels with the finding so you can see why it is trustworthy, not just that the model said so.
5

Memory

Finally, the finding is weighed against what Sigilix has learned about this repo — taught rules and prior dismissals. A finding that contradicts a learned rule (“we use integer cents here”) can be suppressed or down-weighted before it posts. See Conversational Learnings.

​
Proof tiers: the receipt every finding carries

Gate 4 attaches a proof tier to each finding that survives. The tier is a pill on the posted comment. It replaces any single number — believability is about how the finding was established, not a 1-to-5 score.

VERIFIED

Checked by execution or backed by a signed receipt. The strongest tier — the claim was demonstrated, not just argued.

GROUNDED

Anchored to cited code and evidence that the provenance and refute gates confirmed. The finding points at real code that supports it.

MODEL

Model judgment. The finding cleared the earlier gates but rests on the specialist’s reasoning rather than an execution check or a hard anchor.
The tiers are a hierarchy of how a finding was established, from a demonstrated result (VERIFIED) down to reasoned judgment (MODEL). Every posted finding wears one, so the tier itself tells you how far to trust it at a glance.

​
Contrast: two stages versus five gates

The field's two stages

Model produces text → text becomes a comment. Nothing checks whether the finding cites real code, matches the diff, or survives refutation. Hallucinations pass straight through.

Sigilix's five gates

Evidence → provenance contracts → refute/execute → proof-tier receipts → memory. A finding cannot post unless it earns it, and it arrives wearing the receipt that says how.

Review Provenance

Proof-tier receipts and the refute/execute stage in detail.

The Synthesizer

How Harmonia cross-references, calibrates, and renders surviving findings.