PLATFORM

Not a feature. The control plane for financial data.

The pipeline you see on the home page runs on a full platform: ingestion, document and meeting intelligence, entity mastering, an agent layer, search, governed review, reporting and distribution. Ten capabilities, one system, from document to system of record.

01 / CAPABILITY MAP

Ten capabilities, one platform.

Each of these is a capability a competitor sells as a whole product. ADI runs them as one system, with the same governed data flowing through every one.

01

Ingestion & connectivity

Email, cloud drives, SFTP, document portals, FIX message logs and data-warehouse connectors, all flowing into a versioned store.

EMAIL · PORTALS · SFTP · WAREHOUSES
02

Document intelligence

OCR, a classification taxonomy, schema-driven extraction into runtime-typed models, a self-service extraction wizard and zero-shot named-entity recognition with a feedback loop.

OCR · SCHEMA-DRIVEN · EXTRACTION WIZARD
03

Meeting intelligence

A staged transcript pipeline: entity and role association, pitch-field extraction with citations, insight, labeling, and a QA stage that validates every CRM writeback against source before commit.

6-STAGE · WRITEBACK QA · ANTI-HALLUCINATION
04

Entity resolution & master data

Ensemble matching with adaptive confidence, graph clustering, and golden records tied to your source of truth, enriched from commercial reference universes like S&P Capital IQ, Preqin, Cherre and ICE, with public identifiers (LEI, FIGI) layered on where they exist.

GOLDEN RECORDS · SOURCE OF TRUTH
05

AI agents & analytics

A sandboxed code-generation agent over 37 audited finance tools; a multi-LLM chat layer; a visual Agent Builder; plain-language questions compiled to SQL; NL to dashboard; an MCP server for external AI clients.

ANALYST AGENT · AGENT BUILDER · 37 TOOLS
06

Search & RAG

Per-tenant vector collections, dual chunking strategies and a semantic catalog, five collections per vertical across assets, documents, summaries, entities and parties.

PER-TENANT · SEMANTIC CATALOG
07

Workflow & human review

Maker-checker task queues with field-level edits, approve and reject, and a full audit trail, on an orchestrator with a scheduler, event router and autoscaler.

MAKER-CHECKER · AUDIT · ORCHESTRATION
08

Reporting & BI

NL to SQL, drag-drop dashboards, charting and PDF export, holdings and ownership graphs, valuation and a query lab, plus RAG-driven branded Word and PDF report synthesis.

NL→SQL · DASHBOARDS · HOLDINGS · BRANDED PDF
09

Data distribution

A distribution layer with governed reader accounts, table sharing and reporting-client provisioning, white-label data delivery on top of verified data.

GOVERNED SHARES · READER ACCOUNTS
10

Security & platform

Per-tenant isolation, role-based access by organization and department, secret management, configuration services and platform-wide observability.

TENANT ISOLATION · RBAC · OTEL
02 / ENTITY MASTERING

The capability that makes every other one trustworthy.

A number is only as good as knowing which entity it belongs to. This is the layer aggregation tools skip, and the reason ADI's data can be acted on.

Three systems write the same fund three different ways. ADI resolves all of them to one record, tied to your source of truth.
A short name on the custodian feed. The full legal entity on the capital account statement. An abbreviation in the PortCo report. Ensemble matching with adaptive confidence bands, graph clustering and golden records resolve all three to the same master record, anchored to the system you treat as the source of truth, enriched from commercial reference universes like S&P Capital IQ, Preqin, Cherre and ICE, with public identifiers (LEI, FIGI) layered on where they exist. Mismatches route to a human; everything else is automatic.
entity_resolution · fund names redacted
alias_1Sample Fund IX
alias_2Sample Capital Fund IX, L.P.
alias_3SCF Fund 9
masterGR-0417 · your source of truth
identifiersLEI · FIGI resolved
confidence0.98 · auto
03 / THE AGENT LAYER

Already agentic. The rails are the point.

The agent is a commodity. Everything that makes an agent safe to act on financial data, typed schemas, identifier grounding, a human review gate and a writeback-QA stage, ADI already built. That is the layer the frontier vendors do not have.

[ ANALYST AGENT ]

A code-writing analyst

An agent that writes Python in a sandbox against 37 registered finance tools, every call audited to a log, with model routing by job.

37 TOOLS · SANDBOXED · FULLY AUDITED
[ AGENT BUILDER ]

Workflows you compose

A visual builder for supervised background agents: document extraction, data movement from documents to the GL or the GL to portfolio monitoring, feed reconciliations, root-cause analysis on breaks.

NODE CANVAS · SCOPED · EXTENSIBLE
[ SUPERVISION ]

Every action gated

Agent-proposed actions land in the same maker-checker queue a human already uses. Nothing reaches your system of record unreviewed.

MAKER-CHECKER · APPROVAL GATE
Agent census
Autonomy
Tool reach
Gov
Analyst Agent
A1 / A2
Read · Create · Act
3
Meeting-transcript agent
A2
Act · QA-gated
4
Document-extraction agent
A2
Write via review
4
Conversational RAG chat
A1
Read
3
NL→SQL query agent
A1
Read (SQL)
3
Reporting & dashboard agents
A1 / A2
Create
2
A LIVING REGISTRY · 12 LLM-DRIVEN ACTORS IN THE CODEBASE · THE TWO HIGHEST-GOVERNANCE AGENTS ARE THE ONES WHOSE OUTPUT PASSES A VERIFICATION GATE
04 / INTELLIGENCE

Verified data is data you can finally ask questions of.

Once every field is extracted, mastered and checked, two things come for free: a portfolio you can query in plain language, and reporting that builds itself from numbers you already trust. Questions compile to SQL and run against governed tables: the model writes the query, the database does the math, so answers are deterministic, auditable and cheap to run at volume.

ask · portfolio intelligenceLIVE
What's our total unfunded commitment across private equity?
ADI · ANSWERED FROM VERIFIED DATA
Across 14 active PE funds, total unfunded commitment is $127.4M, concentrated in three 2024-vintage funds.
FUNDUNFUNDED
Growth Equity IX$41.2M
Buyout Fund VIII$33.8M
Technology Fund XV$28.1M
SOURCE · 14 CAPITAL ACCOUNT STATEMENTS · Q2 2026 · EACH FIELD TRACEABLE · FUND NAMES REDACTED
Ask about positions, exposure, commitments…ASK →
report · exposure by strategy · auto-generated

Portfolio exposure by strategy

Private equity38%
Private credit26%
Real estate19%
Venture11%
Hedge funds6%
BUILT FROM VERIFIED POSITIONS · NO MANUAL ROLL-UP · REFRESHES ON EVERY NEW STATEMENT · EXPORT TO BRANDED PDF OR GOVERNED SHARE
05 / MODEL AGNOSTIC

The intelligence runs on any model. The layer underneath makes it trustworthy.

Models change every quarter. ADI does not bet the platform on one.

The model reads. ADI is the verification layer that makes the answer safe to act on.
Bring your own model, or use ours. The frontier vendors all ship strong extraction now, so raw capability is not the differentiator. Grounding every answer in typed schemas, mastered entities and a human-checked audit trail is. ADI selects the right model for each job, with a bias to open-source models where they meet the bar: lower cost, and documents that never leave your environment.
model routing · your choice or ours
Open source / self-hostedPREFERRED
Anthropic ClaudeCONNECTED
OpenAI GPTCONNECTED
Google GeminiCONNECTED
06 / HEAD TO HEAD

Where the platform shows.
Aggregation stops. ADI keeps going.

Aggregation platforms are strong at the top of the stack: portals, categorization, extraction. Everything below that is where ADI separates: higher accuracy, end-to-end automation, deployment in your control, no managed-services layer, and a lower total cost.

Capability
Aggregation platforms
ADI
Portal and inbox collection
Yes
Yes
Categorization and organization
Yes
Yes
Field extraction
Yes
98% out of the box
GL integration
Yes
Yes
Data quality validations
Partial
Built in
Feed and statement reconciliation
Partial
Built in
Maker-checker review in your control
Vendor-side only
Built in
Processing in your environment
No
Your cloud or on-prem
Document management and catalog
Partial
Built in
Agentic document automation
No
Built in
Search across documents and data
No
Built in
Conversational AI
No
Built in
Report builder
No
Built in

Bring your stack. See the platform run on it.

A working session on your real documents and systems, across the capabilities your team needs most.