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
Product

The whole corpus, over an API, cited on every value.

A REST API over the same provenanced facts that power every human surface, so the data your tools consume carries the filing on every value and your own product inherits the provenance.

Request accessSee the platform
What you get

The whole corpus, programmatic, cited on every value.

The same corpus, not a thinner feed

A REST API over the identical facts behind the workspace, the models and the add-in, so you build on the full dataset.

Every value carries its filing

Each response names the source document, so a figure in your own product can be audited, not just displayed.

As-reported and standardized

Ask for the comparable view or the filer's own captions, per call, on one crosswalked model.

The document layer too

MD&A, press releases and transcripts as structured records, so text pipelines have a sourced feed.

One vocabulary with the add-in

The same field catalogue as Excel, so a convention learned in one place carries to the other.

Entitled to your licence

Responses resolve to exactly what your organisation licenses, the same scope as every other surface.

See it

A GET, and the value arrives with its filing

GET /v1/fact
{
  "ticker": "AAPL",
  "field": "revenue",
  "period": "FY2025",
  "value": 416161000000,
  "unit": "USD",
  "filing": "10-K",
  "accession": "0000320193-25-000073"
}
Why it earns its place

What it solves.

Each one starts from a real problem on the desk, and what the product does about it.

Same corpus
the full feed
Problem

A data API often hands you a thinner feed than the screens the vendor sells.

Solution

This is the same corpus behind the workspace, the models and the add-in. Nothing is held back.

Every value
carries its filing
Problem

Pull a number through an API and you usually lose the source you would need to trust it.

Solution

Every response carries its filing, so a figure in your own product can be checked, not just shown.

One vocabulary
shared with the add-in
Problem

Every integration invents its own field names, and the mapping drifts over time.

Solution

The field catalogue is the same one the Excel add-in uses, so what you learn in one place works in the other.

What it does
  • A REST API over the same corpus that powers every human surface.
  • Every response carries the filing reference, so answers are checkable.
  • One mnemonic vocabulary shared with the Excel add-in.
  • Entitled to exactly what your organisation licenses.

Live  REST, cited on every value.

How it works

Connect

Point your tools or your model at the API.

Query

Ask for a fact, a statement or a whole dimension.

Trust the answer

Each value arrives with the source filing attached.

The AI layer

The model never does the math.

On ABI Nexa, AI retrieves and explains. It does not invent the numbers, and it cannot pass off a figure it did not fetch.

The math runs in the engine, not the model

Valuations and calculations run in a deterministic engine that reproduces the same result byte for byte. The model narrates that result and checks it for sense; it never produces the number itself.

Every figure resolves to a source

A guardrail checks that each number in an answer traces back to a retrieved cell in the corpus. If it does not resolve, the answer is refused rather than guessed.

Grounded, with the filing attached

Retrieval is scoped to the companies, periods and documents you asked for, and every claim carries the filing, accession and location it came from.

Tested before it ships

A fixed set of questions with known answers runs on every model and prompt change, so a regression is caught by us, not by you.

Works well with
⚖

Methodology

How every figure here is verified, and the exceptions we publish.

▣

Coverage

What we hold, stated and dated, per market.

☷

Products

Every surface, one provenanced corpus.

Start from the filing, not a blank spreadsheet.

ABI Nexa is licensed by organisation. Tell us what you cover and we will come back to you.

Request accessSign in