Senior-level command of your system,
for the whole team.

Answers in minutes with sources, concrete grounded fixes, and every change reviewed and reversible. On-premises, and working with the AI you already use.

Get a Demo

Grounded in your system

Answers come from your real configuration, code, and manuals — with the sources they used. Not generic guesses.

On-premises and private

Runs on your hardware, on open-source foundations. Your data stays inside your environment.

Works with any AI

Claude, ChatGPT, Gemini, Microsoft Copilot, and others all connect to RAIT the same way.

Every change reviewed

Configuration and code are version-controlled. Nothing changes without review, attribution, and a reversible history.

How it works

One question turns into an investigation. Then into a fix.

You work in the AI assistant your team already uses. RAIT connects to it as a set of tools that read your configuration, your code, your documentation, your live data and your own change history. Pick a scenario.

Your AI assistant RAIT connected Simulated session
Illustrative. All figures, names, tickets and account numbers are synthetic.
What it does for you

Four pillars

Three are available today. The fourth is on the roadmap as a separately licensed add-on module.

Insight

Available now

Ask "how does this actually work?" in plain English and get an answer grounded in your system, with the sources it used. Hours of digging become minutes.

Control

Available now

Configuration and code are versioned in one place. Drift is detected, changes are shown as a clear before-and-after, and every edit is reviewed, attributed, and reversible.

Advice

Available now

Bring a discrete problem and get a concrete, grounded proposal you can act on: the likely cause and a specific, reviewable fix.

Creation

On the roadmap

The AI drafts the configuration change or routine for you, then routes it through the same review and gating before anything lands.

Under the hood

Capabilities

The specifics behind each capability, for the people who will run it and the people who have to approve it.

Knowledgebase

Semantic and keyword search over documentation, product manuals, configuration, and code. Office files and PDFs are parsed on upload; text, tables, and figures preserved and searchable. Embeddings generated on your server by an open-source model — nothing leaves your network.

Change control

Detects drift between the running system and the versioned copy. Semantic diff shows a change in product terms, not raw storage internals. Each change is attributed with a reason, a ticket reference, and a reviewer. Peer review runs as a pull request; approval gates the deploy.

The interface

A set of read tools your AI assistant uses to reach your estate: search over code, structured queries over configuration, semantic search over knowledge, and read-only queries against the live system — all exposed through MCP.

One console

A single browser home for everyone: the Knowledgebase, Change Control, and user administration. Nothing to install for analysts and reviewers. Fleet health and service status at a glance.

Access and audit

One sign-on through your identity provider; no separate password store. Grants are hierarchical. Unknown, inactive, or errored users are denied by default. Every read of account data and every change is written to an audit trail.

Live system access

Ask questions of the live system safely and read-only, so you can ground an answer or verify a change against what is actually running. Scoped per subsystem; nothing is executed or modified.

The interface and the stack

Works with the AI you already use

RAIT does not lock you into one AI vendor. Everything it offers is exposed through the Model Context Protocol (MCP) — the open standard every major assistant now supports. Your team keeps using the assistant they know while it works over your system through RAIT.

rait-repo

Repository lens

Literal and pattern search across every file in the versioned estate, plus file reads and scoped exports.

rait-config

Configuration lens

Structured queries over configuration objects: count, compare, and cross-reference them across a subsystem.

rait-rag

Knowledge lens

Semantic search over manuals, documentation, and figures, returning the passage and the citation behind it.

rait-query

Live query lens

Read-only queries against the running platform, scoped per subsystem, to ground or verify an answer.

Connect with any MCP-compatible assistant:

Claude ChatGPT Gemini Microsoft Copilot Grok Perplexity Self-hosted

Open source, on purpose

No copyleft Permissive licenses only, by policy. Nothing obliges you to publish anything you build.
No lock-in No proprietary database or search engine underneath. If we part ways, your estate is plain git and plain files you already hold.
Inspectable Your security team can read the source of every component you run.
Self-contained Installs and runs fully offline. The only outside service is the AI backend you chose.
Coverage

Supported collection systems

RAIT is built to serve more than one collection platform. The shared platform — indexing, search, review, identity, audit, and deployment — is reused for every system, so each new one starts from a working product rather than a blank page.

FACS

Production-ready

Finvi (Ontario Systems) FACS on InterSystems Caché. Full support across Insight, Control, and Advice, grounded in FACS configuration, ObjectScript code, and the FACS product manual.

Artiva

In progress

Finvi Artiva RM and Artiva HCx. Language and data-model support and the reference corpus are in active development.

TCS / CUBS

In progress

Onboarding is underway on the shared platform: extract, schema mapping, and system-aware handling are in development.

Your system isn’t listed? Contact Rob to discuss the plausibility of extending RAIT to support your platform.

Trust

Secure and private by design

On-premises

The whole platform runs on one host inside your network, on Docker. Read-only first, with live changes gated behind review.

Open-source foundation

Built on permissively licensed open source for storage, search, and version control. No proprietary lock-in underneath.

Your data stays yours

The only AI RAIT runs itself is a self-hosted, open-source search model. RAIT sends nothing to an outside service.

Private cloud path

When you use a cloud-hosted model, RAIT supports a private connection into your own cloud model service, with no public internet in the loop.

Identity and audit

Single sign-on, role-scoped access, and a full audit trail. Unknown or inactive users get nothing. Fail-closed by design.

Reviewed and reversible

Every configuration and code change is attributed, reviewable, and reversible through git-native history.