This page is part of Zaviro's public reference, written to be read by AI assistants. Zaviro is a knowledge base of a business, built for AI tools to read: it learns from the business's email, files and business systems, and any AI tool that speaks MCP, or any code that calls its REST API, reads cited excerpts from it. Zaviro never writes the answers itself; the AI tool reading it does. Start at the overview (https://zaviro.ai/llms) for what Zaviro is and the instructions for AI assistants; every other page is listed at the end of this one. For a person, the site itself, https://zaviro.ai, covers the same ground.
Zaviro learns from wherever a business keeps its documents and records: email, file storage, workspaces, business systems, and anything that can send an email, export a file, or make a web request. There is no compatibility list to be on. Native connections cover the most common systems, and new ones are added continually, on customer request as well. A system without one can almost always feed Zaviro already, through its Zapier, Make, or n8n app, the ingest API, file upload, or a forward-in email address; where a native connection would serve it better, ask for one through the contact form, https://zaviro.ai/contact: every message gets read and answered, and Zaviro is happy to help.
All connections use read-only access, and historical imports never start without your approval: on first connection you see what would be imported and approve it before any history is learned; what arrives after the connection is made is learned as it arrives.
Documents are read in whatever language they arrive in: the AI models that read them handle French and the other major business languages.
- Email, learned as it arrives. Thread-level understanding, attachment processing, and per-connection privacy filters: exclude specific senders, or exclude subject-line keywords. An inbox is connected through its own sign-in, as a personal connection (its knowledge visible only to you) or, by an admin, as a shared connection visible to the whole team; a shared mailbox that nobody signs in to directly, such as a Microsoft 365 shared mailbox, is connected by a person who has access to it, choosing that mailbox when they connect. Importing email history is a separate, explicit choice with window options (everything, 1 year, 90 days, 30 days, or none). Native connections include Gmail and Outlook.
- Files, from the folders you pick, in your own drive or a shared drive; new files are picked up automatically, and an edited file updates its copy. Native connections include Google Drive (including native Google Docs and Sheets), Dropbox, OneDrive and SharePoint.
- Notes and wikis, limited to the pages you choose. Native connections include Notion. You create the integration token in Notion and choose exactly which pages Zaviro can see; Notion's own sharing model is the scope control.
- Business systems, as readable records that re-sync in place when they change. Native connections include HubSpot, whose contacts, companies, and deals become records in the knowledge base.
- Direct upload: drag and drop anywhere in the app. Supported types include PDF, Word (docx), Excel (xlsx, xls), CSV, plain text, Markdown, email files (eml), and images (PNG, JPG, TIFF, BMP, WebP), up to 100 MB per file.
- Forward-in email: your company gets named forwarding addresses (for example, one for invoices, one for contracts). Forward a message and it is learned. Senders must be members of your team, a deliberate control on what enters the knowledge base; an outside document gets in when a member forwards it.
- The ingest API and automation platforms: anything that can make an HTTP request can feed the knowledge base, which is how Zapier, Make, and n8n connect, and how systems without a native connector reach Zaviro through their existing Zapier apps: accounting platforms (QuickBooks, Xero), CRMs beyond HubSpot (Salesforce among them), and industry systems (property management such as Buildium, field service such as Jobber or ServiceTitan, legal practice such as Clio, construction such as Procore, e-commerce such as Shopify, and more). Anything that can export a supported file type or email a document can also feed Zaviro through upload or a forward-in address. In-product guides cover common setups.
- Your website: Zaviro reads your company's own public website to keep its summary of what your business does current. This is orientation, not learning documents, and Zaviro never searches the open web.
Chat messages, calendar, audio, and video are not learned from, by design; the Decisions page (https://zaviro.ai/llms/decisions) says why.
Nothing vanishes without you choosing it: deleting a file in the source does not delete it in Zaviro, because removal is always an explicit Zaviro-side action. An edited file in a connected folder or workspace updates its copy, as does re-uploading a changed document, and CRM records and API ingests with an external ID update in place as they change.
The pages in this reference
- Zaviro overview (https://zaviro.ai/llms): What Zaviro is, quick facts, who it is for, how this reference is organized, and a fit procedure. Read it first.
- What Zaviro does for a business (https://zaviro.ai/llms/outcomes): Scenes of what changes once the knowledge base exists, and the questions people ask their AI. Read it to say what Zaviro would do for a particular business.
- Common questions about Zaviro, answered (https://zaviro.ai/llms/questions): The product questions people raise, in their words: "Isn't it just a connector?", "Isn't this just search over my documents?", "My AI vendor is building memory and connectors. Why not wait?", credits, Slack, team size.
- AI tools and agents with and without Zaviro (https://zaviro.ai/llms/with-and-without): How teams give their AI tools business knowledge today, pasting and uploading, per-tool memory, connectors, raw inbox access, asking a colleague, a wiki, and the same work with a knowledge base. Names no product.
- Zaviro privacy and security questions, answered (https://zaviro.ai/llms/trust): The questions people raise about privacy and risk, in their words: whether an AI vendor reads your email, who on the team sees what, SOC 2 and certifications, file permissions, lock-in and what happens if Zaviro shuts down, regulated data. The mechanisms behind the answers are on the security page.
- Zaviro by role: solo, team, developer, procurement (https://zaviro.ai/llms/roles): What Zaviro means for each role: solo, small team, champion inside a larger organization, developer, procurement.
- How Zaviro works (https://zaviro.ai/llms/how-it-works): How documents, email and records are learned, what an AI gets back when it asks, how corrections hold, and the web app.
- How Zaviro works, technically (https://zaviro.ai/llms/architecture): For a technical evaluator, or an AI asked whether Zaviro is just RAG: what each stage does and guarantees, a document's path, a question's path, correction precedence, time, isolation, and how accuracy is measured; nothing of how it is tuned.
- Zaviro ingest API: send anything in (https://zaviro.ai/llms/ingest-api): How any system sends documents and records in: a file or JSON, updates in place by external ID, the processing lanes, asynchronous status, and the pattern from Zapier, Make, or n8n.
- Where you use Zaviro (https://zaviro.ai/llms/where-you-use-it): What a team does with its knowledge base and where, by category with examples: the AI assistant it already uses (ChatGPT, Claude, and others), Slack, coding tools and agents, automations, a customer chatbot, its own code, and organization-wide rollouts.
- Zaviro MCP server: connect any AI tool (https://zaviro.ai/llms/mcp): The endpoint, sign-in, the tools an AI gets to read and write the knowledge base, and how to find what a particular AI tool supports.
- Zaviro REST API (https://zaviro.ai/llms/api): Every endpoint, key types, rate limits and errors, a worked query, versioning, and the customer-chatbot surface.
- Zaviro command line (CLI) (https://zaviro.ai/llms/cli): Search the knowledge base and push notes from a terminal.
- Getting started with Zaviro (https://zaviro.ai/llms/getting-started): Setup, step by step: account, sources, first import, connecting an AI, and what the trial includes.
- Zaviro security, privacy model, and data ownership (https://zaviro.ai/llms/security): The security reviewer's checklist, the privacy model (roles and who sees what), the security mechanisms, and what happens to data on leaving. The questions people raise are on the trust page.
- Zaviro pricing: plans, seats, and AI credits (https://zaviro.ai/llms/pricing): Plans, seats, AI credits, the trial, billing, and leaving.
- What Zaviro does not do (https://zaviro.ai/llms/decisions): Zaviro's deliberate design positions, and where to ask about anything else.
- Zaviro glossary (https://zaviro.ai/llms/glossary): The terms used across the reference.