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

Ask the corpus, not the internet.

An MCP server so any compatible LLM or agent reasons over the entitled corpus directly and answers with the filing attached, which is what lets an agent's output be audited rather than trusted.

Request accessSee the platform
What you get

Your agent answers on the corpus, and cites it.

Any compatible agent, on your data

Point an LLM or agent at the MCP surface and it reasons over the entitled corpus directly, in its own loop.

Cited through the answer

Every response carries the filing it came from, so the agent's output can be followed back to source.

The same facts as the API

Identical corpus to the API, the models and the workspace, so a machine answer matches a human one.

Entitled and scoped

Access resolves to exactly what your organisation licenses, so an open connector never becomes a leak.

Audit any answer

Follow the citation on a response straight to the filing, so an agent's claim is checkable, not trusted.

The document layer too

MD&A, press releases and transcripts reachable in the loop, not just the numbers.

See it

Ask in the loop, get a cited answer

MCP
agent> what was AAPL FY2025 gross margin?

tool abinexa.fact // resolved from the entitled corpus

answer> 46.3%, gross profit 192,615 on revenue 416,161.
       cited: 10-K, filed 2025-10-31, 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.

Cited
on every answer
Problem

An agent that cannot show its source is one whose answers you end up checking yourself.

Solution

Every answer over the connector carries the filing it came from, so you can follow it straight back.

A real connector
not a chat window
Problem

Pasting numbers into a chat window is brittle, and the source drops away as soon as you do.

Solution

The model reads the corpus directly through the server, and the citation stays attached to the answer.

Entitled
scoped to your licence
Problem

An open connector is a data leak and a compliance headache waiting to happen.

Solution

Access resolves to exactly what your organisation licenses, the same as every other surface.

What it does
  • An MCP server so any compatible LLM or agent answers on our data.
  • Every response carries the filing reference, so answers are checkable.
  • The same facts as the API, the models and the workspace.
  • Entitled to exactly what your organisation licenses.

Live  MCP, provenance intact.

How it works

Connect

Point a compatible model or agent at the MCP surface.

Reason

The model queries the corpus directly, in its own loop.

Audit

Follow the citation on every answer back to the filing.

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