Who buys
The people who own the research budget
- A PM or director of research
- The COO or CTO
- The central research or data team at a multi-manager
- The head of data for quant strategies
Acceptance-tested on your own documents · #1 on NetArena MALT (third-party-run)
From the filing to cited model drivers —
Hedge funds
From the filing to cited model drivers —
on the restated basis.
In earnings season, analysts update dozens of models by hand, and the classic error is a growth rate computed against a prior period that has since been restated. The API reads the filing, returns every driver with its page, computes on the right basis, and shows you both figures when a period has been recast.
Who it’s for
Fundamental, event-driven, macro and quant.
Single-manager funds and multi-manager platforms — the desks and data teams that turn filings and releases into model inputs under time pressure.
Who uses
The people who update the models
- Analysts
- Economists
- Data engineers
- Quant researchers
Jobs we do for you
Every driver with its page, on the right basis.
Each job starts from documents your desk already reads and ends with figures that carry their page, their calculation and any conflict between periods or versions.
Job 1 · Fundamental long/short
Earnings-season model updates
- Documents
- Quarterly and annual reports, earnings releases with non-GAAP reconciliations, investor presentations, prior filings.
- What you get back
- Segment revenue and margins, company-specific KPIs, guidance ranges, non-GAAP bridge items, share count and debt maturities, each with its page.
- Year-over-year and quarter-over-quarter changes on the restated basis, with the calculation.
- Recast periods flagged, with old and new values side by side.
- Guidance compared with prior guidance, both cited.
- Measured by
- Time from filing to cited drivers.
- Cells your analyst changes afterwards.
- Restatements caught.
- Names covered per analyst in peak week.
- Start with
- Early Adopter for a pod or sector team.
Job 2 · Event-driven, special situations, distressed
Deal and case sheets
- Documents
- Merger proxies and registration statements and their supplements, merger agreements, credit agreements and indentures, bankruptcy monthly operating reports, disclosure statements.
- What you get back
- Disclosed projections cited by filing version, with changes between versions flagged.
- Implied multiples and deal spread with the calculation, and exchange-ratio and collar terms cited.
- Monthly cash series from operating reports, each month cited.
- Covenant capacity computed from the agreement’s own definitions.
- Measured by
- Time to a cited deal or case sheet.
- Version changes caught.
- Start with
- Early Adopter for an event-driven desk.
Job 3 · Macro
Research series with vintage and basis stated
- Documents
- Statistical releases, central-bank and treasury publications, budget documents, foreign statistical agencies, scanned historical archives.
- What you get back
- Every data point cited, with its vintage (first print or revised) and its basis (seasonally adjusted or not, nominal or real, fiscal or calendar).
- The transformation you specify — growth, inflation or currency adjustment — with its calculation.
- Revisions between vintages flagged.
- Measured by
- Time to build a new research series.
- Vintage and basis errors on a checked sample.
- Series you can’t get from standard databases.
- Start with
- Early Adopter for a macro team.
Job 4 · Quant and data teams
Point-in-time datasets
- Documents
- Filings and releases across your universe.
- What you get back
- Point-in-time datasets — as first reported and as restated — each value cited with its document and filing date.
- Company-specific KPIs across a universe.
- Trace-to-source checks on a sample of an existing vendor dataset.
- Measured by
- Cost and time per dataset.
- Error rate on an audited sample.
- Point-in-time correctness.
- Start with
- Enterprise. Dataset builds run under agreed volumes. Early Adopter covers research use by one team, not systematic dataset building.
Acceptance test
How we’d prove it on your documents.
We replay work your desk has already finished, on your names and your series, and score the output against the answers you already trust.
Fundamental
Your last two earnings seasons
Replay the last two earnings seasons for a set of your names. The answer key is your analysts’ final models.
Macro
Series you already trust
Rebuild series that already exist in a trusted vintage database and compare them point by point, plus a hand-checked sample from scanned archives.
Quant
A hand-verified sample
A hand-verified sample of companies and years, plus filing-date checks for point-in-time correctness.
Pass criteria are agreed before the run, and we report the results as measured, misses included.
Questions we hear
What PMs, COOs and data heads ask first.
“Our questions reveal our book.”
Your documents and questions are used only to provide the service to you, never to improve it for another customer. Enterprise can be deployed in your cloud account or on-premises; the data flow for each option, including any service providers, is documented before you sign.
“We already pay for standardized fundamentals.”
Keep them. This answers from the document itself — including the KPIs no feed standardizes — and shows you both pages when a period has been recast.
“Filing-day speed matters.”
We measure it in your acceptance test, on your names.
“MNPI and information barriers.”
Answers come from the documents you provide, and every figure cites its page. Your barriers stay in your systems.
“Our quants could build this.”
Then run the acceptance test head to head against your internal build, with the pass criteria agreed in advance, and decide on the results.
Which license fits
One desk first. Platform-wide when it passes.
Research teams working on public documents start with Early Adopter. Platform-wide deployment and systematic dataset building run under Enterprise.
Early Adopter · $20,000
A desk, pod or macro team
Working on public documents. Six months, hosted by One Jump.
Buy Early AdopterEnterprise · $1,000,000
Platform-wide, or dataset builds
Inside your perimeter, or dataset builds for quant and data teams under agreed volumes.
Plan EnterpriseCustom pilot · $40,000–$75,000
A filings-watch agent
An agent that watches new filings for your coverage list and pushes cited drivers into your models.
Ask about a pilotEARLY ADOPTER
Self-serve order
Early Adopter API license
One team, one workflow, hosted by One Jump. Start this quarter.
Six-month license$20,000
- API license for six months
- Six months of hands-on development support
- Your documents loaded at onboarding
- Acceptance plan on your own documents, agreed in week one
- Kickoff and keys within 5 business days of a verified order
- Pay by card, ACH, wire or purchase order
ENTERPRISE
Contract-first
Enterprise license
Firm-wide, in your environment, or inside your platform.
Twelve-month license$1,000,000
- Twelve months of development support with a named technical lead
- Deployment in your cloud account, on-premises or hosted, scoped with you
- Custom integrations with your systems
- Documentation for your model-risk and AI-governance review
- Acceptance test on your own documents, agreed in writing before you sign.
- Paid by invoice, ACH or wire in milestones, never by card
Keys are issued to verified businesses after a signed order. No free trial and no low-cost tier — here’s why.
How we prove it
Tested on your documents, not just ours.
Every license and engagement is measured on your own documents and on questions your team has already answered. We agree the pass criteria with you first — figures right within an agreed tolerance, every citation checked against its page, known conflicts flagged — and report the results as measured, misses included.
- Pilots: Acceptance-tested on your own documents before you pay the balance. Fixed fee, capped.
- Enterprise: Acceptance test on your own documents, agreed in writing before you sign.
- Early Adopter: Your acceptance plan is agreed in week one, and six months of development support are aimed at passing it.
A third-party-run result
#1NetArena MALT on AgentBeats
100% / 100%Correctness and safety over 2,500 queries
0.056 sFastest of the perfect runs
A network-policy benchmark, not a finance one. We show it because it’s how we work: define correct, test at volume, publish the run.
Record details Leaderboard Result commit
Standing checked October 6, 2026.
Talk to us
Test it on your names before earnings.
Tell us which names, series or datasets you’d replay, and we’ll come back with a draft acceptance plan. Ready to start with one desk? Order Early Adopter — $20,000.
We reply within one business day. Prefer a call? Book 30 minutes.