# 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.

Training every employee individually wastes time. When one employee learns something, the shared knowledge layer makes it available to the rest of the team automatically. Brief your marketing lead on new brand guidelines once, and the content writer, social media manager, and designer all absorb it instantly. No duplicate training sessions, no inconsistent information.

This works for any type of knowledge: product updates, customer preferences, process changes, competitive intelligence. Your sales lead closes a deal and logs the objection-handling approach that worked. The next time any sales rep encounters the same objection, they already know the winning response.

Shared knowledge respects team boundaries. Marketing knowledge stays within the marketing team unless you explicitly share it company-wide. Sensitive information does not leak to employees who should not have it. You control the scope, and the system enforces it.

## Train Once, Benefit the Entire AI Workforce

When you train one AI employee with new information, that knowledge does not have to stay siloed. Sistava cross-employee shared knowledge lets you propagate what one agent learns to the rest of your team, so the whole AI workforce operates from the same understanding without redundant uploads or manual synchronization.

This is especially powerful for foundational business knowledge: your brand guidelines, your ICP, your product positioning, your competitive landscape. Upload it once to a central knowledge source and every relevant AI agent across every team benefits immediately.

## How Knowledge Flows Across the Team

Shared knowledge works at two levels. The first is explicit propagation: you push a knowledge update from one agent and choose which other agents receive it. The second is passive shared memory: agents on the same team contribute to and read from a common knowledge pool as they work.

This means a Customer Success agent who learns about a new product limitation can write that to shared memory, and the Sales agent will naturally factor it in when qualifying prospects the next day. No ticket, no Slack message, no human coordination required.

Permissions govern what flows where. Sensitive knowledge, like financial data or confidential client information, stays scoped to the agents that need it. Shared knowledge is not a free-for-all, it is a governed distribution system.

## The Compound Effect of a Learning AI Workforce

Individual AI agents get smarter over time through their own memory layers. Shared knowledge creates a compounding effect across the entire team. The more your AI employees work, the more they collectively know, and the less you need to repeat yourself or maintain parallel documentation.

For growing companies, this is a structural advantage. Your AI workforce becomes an institutional knowledge system that persists regardless of team changes, scales without proportional training effort, and applies accumulated intelligence to every new task.

## How It Works

**Agents on the same team share a common knowledge base so information learned by one is available to all.**

When an agent learns something about your company, a client, or a process, that knowledge can be shared with every agent on the team. The shared knowledge base is separate from each agent's personal memory, and agents know the difference. Personal insights stay private. Company-relevant facts propagate to all teammates automatically.

This means your Marketing Manager and your Customer Support Lead are always working from the same source of truth. If one agent updates the company positioning, the other sees it. If a client detail changes in one conversation, the whole team reflects that update in the next. No more briefing each agent separately every time something changes.

## Use Cases

### Operations team sharing standard procedures across all agents

Upload SOPs once and every AI employee on the team references the same source. No duplication, no drift.

### Marketing team keeping brand guidelines consistent across agents

Shared knowledge ensures every AI agent writes, responds, and acts according to the same brand standards.

### Customer success team syncing product updates to all agents

When the product changes, update shared knowledge once. All agents immediately reflect the new reality.

### Engineering team giving all agents access to architecture docs

Shared technical knowledge means every AI employee operates with the same understanding of your systems.

## Comparison

| Before | After |
|---|---|
| Each agent has its own knowledge and they drift out of sync. | Shared knowledge is loaded into every agent on the team automatically. |
| Updating information means editing each agent one by one. | Change shared knowledge once and all agents reflect it immediately. |
| Inconsistent answers across agents confuse users and break trust. | Every AI employee draws from the same source of truth. |
| Managing knowledge at scale becomes a full-time job. | One shared library serves the entire team, always up to date. |

## FAQ

### Does shared knowledge mean all AI employees see everything?

No. You control what is shared and who receives it. Shared knowledge is distributed based on relevance and permissions, not broadcast to everyone by default. Sensitive information stays scoped to the agents that need it.

### If I correct a mistake in one agent knowledge base, does the correction propagate?

Corrections to shared knowledge sources propagate to all connected agents on the next sync. Corrections to agent-specific memory must be updated per agent, since that memory was formed through individual experience.

### How is cross-employee shared knowledge different from just connecting the same document to multiple agents?

Connecting the same document to multiple agents handles static content. Cross-employee shared knowledge also captures dynamic knowledge, things agents learn through conversations and tasks, and makes that experiential learning available across the team automatically.

### Can shared knowledge flow between teams, or only within a team?

Both are supported. You can configure knowledge sharing within a single team or across the entire organization. Cross-team knowledge sharing is useful for global policies, brand standards, or company-wide competitive intelligence.

### Can multiple AI employees share the same company knowledge base?

Yes. Shared team knowledge is accessible across all employees in an organization, so every AI agent operates from the same source of truth. You update it once and every agent benefits.

> Our support agent and sales agent now share the same product knowledge. A client asked a technical question to support and got the exact same answer our sales agent gives. Consistency we never had before.
>
> Tyler B., VP of Customer Experience · SaaS company

## Where Shared Team Knowledge fits

Shared Team Knowledge 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: Shared Team Knowledge](/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.
- [Train From Any Source](/en/features/knowledge/knowledge_sources): 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.

## Explore

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