AI document intelligence platform

Ask your company anything.

MOST Insight connects to Microsoft 365, Google Workspace, Dropbox, Box, your desktops and phones — then answers questions from your documents with cited, permission-aware answers. Built by MOST LLC, an AI company.

  • Every answer cites its sources
  • Users only see what they may open
  • Cloud or fully on-premise
2 TB+
documents indexed per deployment
< 3 s
typical answer latency
12
storage platforms connected
100%
answers with source citations
Why MOST Insight

Enterprise search, reinvented with AI

Your organisation already has the answers — buried in policies, contracts, manuals, spreadsheets and mail. MOST Insight finds them, reads them and explains them, with the evidence attached.

Ask, don’t search

Type a plain-language question. MOST Insight reads the relevant pages across every connected source and writes a concise answer with the exact documents it relied on.

Every answer is cited

Each response links to the source documents and excerpts behind it. The AI is instructed to never invent facts — if the answer is not in your documents, it says so.

Permission-aware by design

Access rights from Microsoft Entra ID, Google Workspace and your file systems are indexed with every document. Users only ever see answers built from files they are allowed to open.

Hybrid retrieval engine

Dense vector embeddings and BM25 keyword search are fused for high recall on both conversational questions and exact part numbers, invoice IDs or clause references.

Source tiering

Rank official policies above e-mail threads. Tiered sources let the assistant prioritise authoritative documents and flag contradictions instead of guessing.

Multilingual

Ask in one language, get answers from documents written in another. Built for international organisations with mixed-language archives.

Admin analytics

A pseudonymised question store shows what people ask, where the gaps in your documentation are and what each answer costs — without exposing individual identities.

Open integration API

Expose the assistant to other tools through a REST API and the Model Context Protocol (MCP), so your own agents and workflows can query company knowledge.

Chat where you work

Native web app, Microsoft Teams and Telegram bots, plus desktop and mobile apps. The same permission checks apply on every channel.

See it in action

A conversation with your documents

Ask in plain language. MOST Insight retrieves the right passages, writes an answer and shows exactly which files it used — ranking official policies above casual e-mail.

  • Grounded answers. If the documents do not contain the answer, the assistant says so instead of guessing.
  • Policy precedence. Contradictions between sources are surfaced, with the authoritative one first.
  • Any language. Ask in English about a document written in German, Hungarian or Spanish.
Open the full demo
MOST Insight · Acme Industries workspace signed in as j.doe · 1,284 documents in scope
Hi! I am MOST Insight. Ask me anything about your company documents — try one of the example questions below.
How it works

From scattered files to instant answers in four steps

01

Connect your sources

Authorise Microsoft 365, Google Workspace, Dropbox, Box or any other connector in minutes. Install the lightweight desktop and mobile agents for local files.

02

Index & embed

Our high-performance indexer extracts text from Word, PDF, PowerPoint, Excel, e-mail and more, chunks it intelligently and stores embeddings together with the access rights of each file.

03

Ask questions

Users ask in the web app, Teams, Telegram or on their phone. The engine retrieves the best passages they are allowed to see and generates a cited answer.

04

Stay in sync

Changes are picked up continuously; a full consistency pass runs nightly. Permissions are refreshed on a schedule so revoked access disappears from answers automatically.

MOST Insight architecture: sources, indexer, vector store, AI engine and clientsSOURCESMicrosoft 365Google WorkspaceDropbox · Box · S3Desktops & phonesNetwork sharesIdentity (Entra, Google)Indexercrawl · extract · OCRchunk · embedcapture access rightshigh-performance Rust serviceVector storedense embeddingsBM25 sparse indexper-chunk ACLsprivate per tenantAI enginehybrid retrievalpermission filterLLM answer + citationsNode.js / TypeScriptLanguage modelsAzure OpenAI · privateor on-premise GPUCLIENTSWeb appDesktop appsiOS & AndroidTeams · Slack · TelegramREST & MCP APIAdmin consolevectors + ACLcited answers · only from files the user may opencontinuous sync · nightly full pass
Security first

Built for organisations that cannot afford a leak

Access control is not an afterthought. Permissions are captured with every indexed chunk and enforced on every query, on every channel. Deploy in our cloud, your cloud, or entirely inside your own data centre.

Read about security
Permission-aware retrievalEntra ID, Google and NTFS rights enforced per chunk.
Single sign-onOIDC / SAML with group-based filtering and session hardening.
Encrypted everywhereTLS in transit, encrypted volumes at rest, secrets kept out of images.
Your infrastructure, if you wantContainer stack for on-premise or private cloud with local GPU inference.
Pricing

Simple plans that scale with your team

Flat monthly subscriptions sized by users and indexed data. Pay by card and start today, or talk to us about an enterprise agreement.

Starter

Small teams and professionals

$41 / month

Billed $492 yearly

  • Up to 5 users
  • 25 GB indexed
Start with Starter
  • Desktop & mobile apps
  • 2 cloud connectors (e.g. OneDrive + Dropbox)
  • Cited AI answers
  • Web chat assistant
  • Daily re-indexing
  • E-mail support
Most popular

Team

Departments and growing companies

$166 / month

Billed $1992 yearly

  • Up to 25 users
  • 250 GB indexed
Choose Team
  • Everything in Starter
  • All connectors incl. SharePoint, Google Drive, Box
  • Single sign-on (Entra ID, Google)
  • Permission-aware search
  • Microsoft Teams, Slack & Telegram bots
  • Admin analytics console
  • Hourly incremental sync
  • Priority support

Business

Multi-site organisations

$499 / month

Billed $5988 yearly

  • Up to 100 users
  • 2 TB indexed
Choose Business
  • Everything in Team
  • Source tiering & policy precedence
  • REST API & MCP server access
  • Usage & cost dashboards
  • Custom AI model endpoint (Azure OpenAI / private)
  • Network share & S3 connectors
  • 99.9 % uptime SLA
  • Dedicated onboarding engineer

Enterprise

Regulated and data-sovereign deployments

Custom

Tailored quote · annual contract

  • Unlimited users
  • Unlimited
Talk to sales
  • Everything in Business
  • On-premise or private-cloud deployment
  • Local GPU inference — data never leaves your network
  • Custom connectors
  • Security review & DPA
  • 24/7 support with named success manager

Ready to give your team instant answers?

Start on any plan today, or talk to us about an on-premise deployment for your organisation.