New Product · Verifier
Early AccessVerify every financial claim before it becomes a liability.
Verifier checks AI- and analyst-generated financial claims against primary-source SEC filings. It decomposes each answer into discrete claims, grounds every number to its filing, and returns a per-claim verdict — with citations and an auditable trail.
GAAP coverage today · non-GAAP on the roadmap
The Problem
In finance, an unverified number is a liability.
Whether a figure comes from an analyst or an LLM, if it can't be traced to a filing it can't be trusted. Verifier makes grounding the default — every claim traced to source, or flagged.
Numbers that don't reconcile
Models state confident figures that don't match the filing; analysts transcribe the wrong line item. A single wrong number moves a model or misleads a client.
Citations that don't exist
AI-generated answers reference sources that were never filed or point at the wrong document. An unsourced claim is an unverifiable claim.
Errors that propagate silently
A bad figure is invisible at the output layer. It flows into a memo, a deck, or a downstream model before anyone catches it.
Pipeline
How Verifier works.
Decompose
The answer is parsed into discrete claims — factual assertions and numeric values — each treated as a separate unit of verification.
Ground
Every claim is traced to its primary source: SEC filings and a structured financial-fact corpus built on EDGAR/XBRL. Unsourced assertions are flagged, not assumed.
Check
Reported figures are matched against the filing to a configurable tolerance — exact-to-the-cent for banking — and contradictions between a claim and its source are surfaced.
Score & audit
Each claim returns a verdict, a confidence score, and its citation. Every check is logged to an exportable, hash-backed audit trail.
Capabilities
Available nowWhat Verifier does today — and what it doesn't claim to.
Claim decomposition
Break any answer into individually verifiable claims — factual assertions and numeric values — instead of grading a paragraph as one blob.
Primary-source grounding
Every claim is traced to the SEC filing behind it, on a corpus built with the same EDGAR/XBRL lineage we ran in production at OTC Markets. No source, no pass.
Numeric verification
Reported numbers are checked against the filing to a configurable tolerance, from loose rounding down to exact-to-the-cent. Off-by-a-cent figures are caught, not waved through.
Contradiction detection
Where a claim conflicts with its source — or with the reported figure it cites — the discrepancy is flagged with a plain-language explanation.
Confidence scoring
Each verdict carries an explainable confidence score, so a reviewer knows which claims are settled and which deserve a second look.
Audit trail
What was checked, against which filing, at what time, with what result — logged and exportable for internal review or model-governance documentation.
Capabilities
On the roadmapWhere Verifier is going.
These extend the same engine — decompose, ground, check, audit — with new sources and checks. They are in development, not shipped. We'd rather tell you that than pretend otherwise.
Non-GAAP & earnings-release grounding
Extend beyond GAAP financials to adjusted metrics and their reconciliations, sourced from 8-K earnings exhibits.
Derived-metric recompute
Recompute ratios, growth rates, and margins from a filing's own line items and check the stated value against them.
Intra-response contradiction
Detect where one part of an answer contradicts another, not just where a claim conflicts with its source.
Multi-dimension confidence
Break the confidence score into factual accuracy, numeric precision, and source quality as separate, inspectable signals.
Tamper-evident audit chaining
Chain-anchor the audit hashes so the verification log is provably immutable for regulatory examination.
On-prem & air-gapped deployment
Run entirely inside your infrastructure, including fully air-gapped environments — no data leaves your perimeter.
Who It's For
Built for every team that ships financial answers.
Research & Analysis
Verify AI- and analyst-produced earnings summaries and sector notes against the underlying filings before they carry your research brand.
Compliance & Governance
Keep an auditable record of what was checked, against what source, and when — evidence for model governance and examination.
Wealth & Advisory
Make sure the figures in a client-facing recommendation are grounded and cited before they reach the client.
FinTech & AI platforms
Embed Verifier as a grounding layer behind AI-generated financial output, so the numbers your product ships are traceable to source.
Trust & Grounding
A verification tool has to be verifiable itself.
Primary-source only
Every verdict cites the filing it came from — not a vendor's re-derived number. The citation is the filing, so the audit stands on its own.
Exportable audit trail
Each verification is logged and exportable, suitable for internal review and model-governance documentation. Tamper-evident chaining is on the roadmap.
Deploys in your environment
Runs as an API/MCP service, with a self-hosted option so client data stays inside your perimeter. Your queries are never used to train any model.
Put a verification layer between your AI and your clients.
Verifier is in early access. If you're shipping AI-generated financial answers and need them grounded and auditable, we'd like to talk.
Request early accessGAAP coverage today · non-GAAP on the roadmap