Matching in Brisc is deterministic, rule-based and explainable; AI reads the documents and argues the borderline cases, never the match itself. Every record carries what the AI proposed, what a human chose, and the evidence for both.
Rules. The arithmetic never belongs to a model, which is why the numbers are never a guess.
The same inputs produce the same answer every run, and every match names the rule that made it.
The model extracts from messy documents and argues borderline matches; it proposes, never decides.
Confidence tiers route anything unclear to a person, reasoning and source documents attached.
Two numbers, deliberately kept apart: what posts is 97%+ accurate, because a human clears everything uncertain first. The match rate underneath is a ramp, not a promise.
The honest ramp. 80% of records match on day one; 92 to 95% by about 90 days. At steady state, the review queue is roughly one row in twenty.
Not a confidence score and a shrug. Every extracted value is stamped with the document it came from and a written reason it was read that way, one click from the source file.
A named person, on every record. The loop is audit-grade, not a checkbox.
What the AI proposed and what a human chose, stored side by side, inspectable forever.
Who approved it, when, and what they saw, with a timestamp.
Exceptions carry their own reasoning and sources, worked record by record, never a bulk write-off.
Draft, reviewed, approved, export: nothing leaves while it is still an opinion.
Nothing is guessed, nothing is silently corrected. A record the engine cannot settle gets a place in the queue, and autonomy is earned in stages your team controls, the way a new hire earns it.
No. That is a design decision, not a settings toggle.
Models from multiple providers, the right one per reading job, no single-vendor lock.
Model versions are pinned per tenant; the model reading your bordereaux changes only when you change it.
Your data never trains shared models; what it learns from your corrections stays in your tenant. In full: security and tenancy.
This is the trust story under every Analyst: reconciliation, bordereaux, submissions, claims, cessions. The engine they share: the platform · integrations.
Rules. Matching is deterministic, rule-based and explainable: the same inputs produce the same answer every run, and every match names the rule that made it. AI reads the documents and argues the borderline cases; it never decides a match.
Output accuracy is 97%+, because a human reviews everything the engine isn’t sure about before it posts. The match rate itself is 80% on day one and climbs to 92 to 95% by about 90 days, as the rule base absorbs what the model surfaces. At steady state your team reviews roughly one row in twenty.
It fails open: the record stops and asks. Unmatched rows queue per record with the reasoning and source documents attached. Nothing is guessed, nothing is silently corrected.
On every record: what the AI proposed, what a human chose, the reviewer’s identity, the timestamp, the rule or alias that fired, and a click-through to the exact source document behind each value. The full trail is exportable.
Your data never trains shared models. What the platform learns from your corrections, rules, prompt tuning, confirmed aliases, stays inside your tenant and belongs to your book. Brisc runs a provider-agnostic model catalog with pinned model versions per tenant, so the model reading your documents doesn’t change under you and nothing you send us leaks into anyone else’s system.
30 minutes, no slide deck. We run your data and you inspect the lineage on every record: what the AI proposed, what a human chose, and the evidence behind both.
Book the walkthrough