ABI NexaIntelligence OS
The data & access layer
ΣFundamentals & Filings DataStandardized and as-reported, citedfxExcel Add-inThe cited number in your model{ }Data APIThe whole corpus, programmatic∞MCP ServerThe AI-native connector⛱Research WorkspaceThe whole file, per name
AI-native deliverables
ΣOperating & Valuation ModelsBuilt, sourced, refreshed on the print▤Company Tearsheets & ProfilesThe as-of-date one-pager✎Confidential Information MemorandaThe sell-side document, drafted✎Investment MemorandaThe buy-side write-up, traceable▣Pitch BooksProfiles and precedents, quoted⚟Screening & Idea GenerationScreens across the corpus
Who we serve
BBuy-SideHedge funds & asset managersSSell-Side ResearchEquity researchIBInvestment Banking & Corp DevM&A and coveragePEPrivate Equity & VCDeal teams, diligence to model▣CorporatesStrategy, IR and FP&A{ }Data & Quant TeamsAgents and pipelines
Plans Methodology Resources Sign in Request access
Products
Fundamentals & Filings DataStandardized and as-reported, citedExcel Add-inThe cited number in your modelData APIThe whole corpus, programmaticMCP ServerThe AI-native connectorResearch WorkspaceThe whole file, per name
Solutions
Operating & Valuation ModelsBuilt, sourced, refreshed on the printCompany Tearsheets & ProfilesThe as-of-date one-pagerConfidential Information MemorandaThe sell-side document, draftedInvestment MemorandaThe buy-side write-up, traceablePitch BooksProfiles and precedents, quotedScreening & Idea GenerationScreens across the corpus
Clients
Buy-SideHedge funds & asset managersSell-Side ResearchEquity researchInvestment Banking & Corp DevM&A and coveragePrivate Equity & VCDeal teams, diligence to modelCorporatesStrategy, IR and FP&AData & Quant TeamsAgents and pipelines
PlansMethodologyResources
Sign inRequest access
Client

Publish with every figure traceable.

Equity research teams refresh the model on the print instead of the weekend after, and publish knowing every number can be traced back to the filing it came from.

Request accessSee the platform
What you get

What you actually get to do.

Editable models in your workbook

A built model per name that you adjust in your own Excel, refreshed in place on the print. No migrating into someone else's template.

The full research file

MD&A, press releases and transcripts beside the financials for every name you cover, so the note writes from one place.

Publish with every figure traced

Any number in the note is one click from its filing, so the note defends itself when compliance or a client asks.

Earnings updates the morning of

When a filing lands the model rolls forward, so the note goes out on the day, not the weekend after.

Cover more names per analyst

The per-name assembly is already done, so initiating and maintaining coverage scales without more late nights.

Notes and data that agree

Your write-up and your data read one corpus, so a figure is the same in the model, the note and the table.

See it

The note, and the numbers behind it.

The refresh, the traced note and the coverage math, on real output. Arrows or dots to step through.

Refresh on the print
Your model rolls to the new filing
When a filing lands, the add-in rolls your own model to the new print in place. You update the note the morning of, not the weekend after, and the structure stays yours.
Excel
// your model, refreshed on the new 10-Q
=NEXA.VAL("MSFT", "revenue", "FY2025Q4") -> 76,441

// recalculate and every live cell rolls forward,
// each keeping its filing, accession and filing date
Every figure traced
Publish, and the note defends itself
Publish knowing any number in the note is one click from the filing it came from. When compliance asks, the note answers for itself.
os.abinexa.com/note/MSFT
Line itemFY2024FY2025
Revenue245,122281,724
Operating income109,433128,528
Operating margin44.6%45.6%
cited 10-K, filed 2025-07-30, accession 0000789019-25-000047
Cover more names
One fact model, less assembly
One fact model behind every name means your notes and your data agree, so coverage widens without paying the assembly tax on each new company.
One fact model, many namesnotes and data, one source
What used to be per-name workOn the platform
Rebuild the model for a new namePrebuilt, cited, ready to adjust
Re-key the quarter after a printRefreshed in place on the filing
Reconcile the note against the dataBoth read the same corpus
Coverage scales with judgement, not with data entry.
In practice

What the deadline stops costing.

01

Refresh on the print

The add-in refreshes your model in place when a filing lands.

not the weekend after
By hand today
Re-key the model over the weekend after a print before you can update the note.
02

Publish defensibly

Every figure in the note traces to its filing, so the note defends itself.

cited to the filing
By hand today
Publish a number you cannot immediately source if compliance asks.
03

Cover more names

The whole file per name, prebuilt, so coverage scales without the assembly.

one fact model
By hand today
Cover fewer names than you would like because each one is heavy.
The surfaces that matter here.
Excel Add-in. Refresh your own model on the print.Company Tearsheets. Editable decks as of any date.Research Workspace. Everything on a name, cited.Operating & Valuation Models. A built model to start from.
Why it fits

Built for a research desk on a deadline.

One fact model

Your notes and your data agree because they read the same corpus, so a figure is consistent across the desk.

Refresh, do not rebuild

The add-in feeds the new print into the model you already trust, in place.

7,500+
pre-built models, US, India and foreign filers
15 years
of history, restatements kept
29.8M
facts, each one cited
0
wrong on the source-verified sample

See it on your own coverage.

Tell us the names and markets you follow and we will show you the desk on them.

Request accessSign in