# Train From Any Source

Train your AI employees on the documents and tools your company already uses: upload files, point at any URL, or connect an app like Notion, Google Drive, Slack, or Zendesk. Training happens in place, with no exporting and re-uploading, and it teaches the whole workspace at once, not just one employee.

An employee is only as useful as what it knows. Knowledge Sources is how everything your company knows gets into your employee's head: upload files, point at a web page, or connect the tools where your documentation already lives.

Connect a source once and training happens in place. Google Drive folders, Notion workspaces, Confluence spaces, SharePoint sites, support desks like Zendesk and Intercom, project tools like Jira and Linear. The employee studies the content and answers from it the same day.

Web pages count as sources too. Give the employee a URL, your help center, your pricing page, a partner's documentation, and it reads and learns the content like any other document.

Everything lands in one knowledge base for that employee, and shared knowledge spreads it across the team. You can inspect what was learned from each source on the Training page, so the brain is never a black box.

## One Knowledge Base, 35+ Sources

Drives and wikis: Google Drive, OneDrive, Dropbox, SharePoint, Notion, Confluence, Coda. Project tools: Jira, Linear, Asana, Trello, ClickUp, Monday. Support desks: Zendesk, Intercom, Freshdesk. CRMs: HubSpot, Salesforce, Pipedrive. Communication: Slack, Discord, Microsoft Teams, Gmail, Outlook. Sites and code: WordPress, Webflow, Medium, GitHub, GitLab, or any URL.

Each connector reads the content where it lives, so there is no export and re-upload routine. Pick the source, choose what to include, and the training pipeline does the rest.

## Upload Files Directly

Sometimes knowledge is a folder of documents: contracts, product specs, research PDFs, onboarding guides. Upload them straight to the employee and they become part of its knowledge base, searchable and quotable in any conversation or task.

Common document formats are supported, and large collections train in the background while you keep working. You see each document's training status on the Training page.

## Point at a URL

Any public web page can be a source. Your help center, your changelog, an industry glossary, a partner's API documentation. The employee reads the page content and learns it like a document.

This is the fastest way to bootstrap a new employee: point it at the pages that explain your product and your market, and it speaks your language from the first conversation.

## Inspect What It Learned

Training is not a black box. The Training page shows every source, every document, and what the employee extracted from each one, so you always know where an answer could have come from.

If a source was wrong or outdated, remove it and the knowledge goes with it. You curate the brain the way you would curate a wiki.

## Private to Your Workspace

Everything an employee learns stays inside your workspace. Trained knowledge is isolated per company, used only to serve your team, and never shared across customers.

Combined with Shared Knowledge, one well-trained employee can teach the whole team: train once, and every employee in the company can draw on the same facts.

## From Scattered Sources to One Answer

Company knowledge rarely lives in one place. The product specs sit in Notion, the contracts in Drive, the customer history in the help desk, and the institutional memory in old email threads. Once those sources are connected, the employee draws on all of them at once.

Ask a question and the answer can synthesize a policy from one source, a precedent from another, and a current number from a third. That cross-source view is something no single human teammate, searching one tool at a time, can match at speed.

## How It Works

**Connect the tools where your knowledge lives, upload documents, or point at URLs, and your employee studies the content into a searchable knowledge base.**

Every source flows through the same training pipeline: content is read from the connector, upload, or page, broken into facts and passages, and indexed into the employee's knowledge base. From then on the employee can answer questions, write documents, and complete tasks grounded in your actual material rather than general knowledge.

You stay in control of the brain. The Training page shows every source and its status, lets you add or remove content at any time, and shared knowledge distributes the result across your whole team.

## Use Cases

### Answer support from your help center

Connect Zendesk or point at your help center URL and the employee answers customer questions grounded in your published docs.

### Bootstrap a new employee in an afternoon

Connect the company wiki and upload the product specs, and the new hire speaks your language from the first conversation.

### Ground sales answers in real product facts

Train on product docs and the CRM so proposals and replies quote actual capabilities and pricing instead of approximations.

### Research across a folder of PDFs

Upload the reports once, then ask questions across all of them: comparisons, summaries, and citations come from the documents themselves.

### Keep client context out of your head

An agency connects each client's Drive folder so any employee can pick up a client's history, tone, and constraints on demand.

## Comparison

| Before | After |
|---|---|
| Company knowledge is scattered across ten tools. | One knowledge base trained from all of them. |
| Every answer needs a human who remembers where the doc is. | The employee quotes the right document on demand. |
| Context gets copy-pasted into every conversation. | Connect the source once and it is always in the room. |
| Generic AI answers that ignore your business. | Answers grounded in your own documents and tools. |

## FAQ

### Which sources can I connect?

Over 35 connectors ship today, including Google Drive, OneDrive, Dropbox, SharePoint, Notion, Confluence, Slack, Gmail, Outlook, Jira, Linear, Asana, Zendesk, Intercom, HubSpot, Salesforce, GitHub, WordPress, and any public URL. File uploads work without any connector.

### What file types can I upload?

Common document formats including PDFs, Word documents, spreadsheets, and plain text. Upload them on the Training page and they train in the background.

### How long until the employee can use new knowledge?

Training runs as soon as a source is added. Small documents are usable within minutes; large collections process in the background and show their status on the Training page.

### Can I see what the employee learned?

Yes. The Training page lists every source and document along with what was extracted from it, so you can audit the knowledge base at any time.

### Can I remove a source later?

Yes. Remove a document or source and its knowledge is removed with it. You curate what the employee knows the same way you would curate a wiki.

### How is this different from Agent Memory?

Memory is what the employee picks up from working with you: conversations, decisions, preferences. Knowledge Sources is deliberate training on documents and tools. They work together: memory for context, trained knowledge for facts.

### Is my data used to train models for other customers?

No. Trained knowledge is isolated to your workspace and used only to serve your team. Nothing you connect or upload is shared across customers.

### Can the whole team share one knowledge base?

Yes. With Shared Knowledge, what one employee is trained on becomes available to the rest of the team, so you train once instead of per employee.

### Can I mix uploads, URLs, and connected apps for one employee?

Yes. All source types feed the same knowledge base, and the employee draws on all of them together when answering or working.

### Does adding more sources slow the employee down?

No. Content is indexed at training time, and the employee retrieves only the relevant pieces per task, so a large knowledge base stays fast.

> We pointed it at our Notion and our help center on Monday. By Tuesday it was answering support questions out of our own docs instead of generic advice.
>
> Lena V., Head of Support · SaaS startup

## Where Train From Any Source fits

Train From Any Source is part of Things that make them smart.

Upload documents, connect Notion or Google Docs, and choose the source content that becomes shared company knowledge. A 6-layer memory system ensures they never forget a conversation, a decision, or a preference. When one employee learns something new, the whole team benefits through shared knowledge.

- [Things that make them smart](/en/features/knowledge): Learns everything. Forgets nothing.

## Read the guide

- [Guide: Train From Any Source](/en/guide/setup/hire)

## More in Knowledge

- [Remember Every Conversation](/en/features/knowledge/conversational_memory): Your AI employees remember what happened in past conversations, across your whole workspace, not just the one they are in right now. Preferences, decisions, and facts shared in chat get carried forward automatically, so you never have to repeat yourself to the same employee, or explain the backstory to a different one. It works out of the box, with nothing to set up or turn on.
- [Keep Notes Between Tasks](/en/features/knowledge/persistent_notes): Every employee keeps a personal notebook of what it has learned about you: your preferences, corrections, contacts, and how you like work done. That notebook loads automatically at the start of every conversation, so you never have to repeat yourself. Update a preference once and it sticks for good, across every future task and every channel.
- [Custom Knowledge Training](/en/features/knowledge/training): Feed your company's existing knowledge into your AI employees so they answer questions and make decisions using your real data, not generic guesses. Train from a connected app (Notion, Slack, HubSpot, and 65+ more), a website crawl, an uploaded file, or pasted text. Training is company-wide: every employee shares the same knowledge base and searches it automatically on every conversation.
- [Train from File Uploads](/en/features/knowledge/training_from_file): Upload a PDF, Word doc, Excel sheet, PowerPoint deck, plain text, Markdown, CSV, JSON, or XML file straight into Training, and every employee on your team can search it within minutes. Up to 20 files per run, each up to 72 MB, feed the same shared knowledge base your employees check on every message. No connected app and no crawlable URL required.
- [Academy Courses](/en/features/knowledge/academy_courses): Sistava Academy is a set of free, self-paced courses that teach you how to get real work out of an AI employee. Each course is a short series of written lessons you read in the browser, no video required, followed by a quiz. Pass the quiz and you get a certificate of completion with your name on it, ready to download as a PDF.
- [Shared Team Knowledge](/en/features/knowledge/shared_team_knowledge): What one AI employee learns in conversation, every employee in your workspace can draw on, automatically. Tell your sales lead about a new pricing rule and your support employee already has it the next time a customer asks, with no retraining and no copy-pasting the same context into each employee. Train an employee on a set of documents (a policy, a playbook, a product spec) and that knowledge is searched before every response across the workspace, so new hires start from what the team already knows instead of a blank slate.

## Explore

- [Every feature](/en/features)
- [Hire an AI employee](/en/market)
- [Pricing](/en/pricing)