Skip to main content
Empower your AI agents with up-to-date, company-specific knowledge by building a Knowledge Group. Each Knowledge Group lets you:
  • Scrape and index content from web pages
  • Upload and process documents
  • Add and manage FAQs
  • Check Knowledge usage in AI agents

What is a Knowledge Group?

A Knowledge Group is a collection of information sources—web content, documents, FAQs—organized for your AI agents to reference. This ensures your agents always have access to the latest, most relevant information.

Why Use Knowledge Groups?

  • Centralize company knowledge
  • Keep information current and consistent
  • Reduce manual training and updates
  • Enable smarter, more accurate AI responses

How It Works

  1. Add web pages, documents, and FAQs
  2. Organize and review your content
  3. Connect to AI agents
  4. Monitor and update as needed

1. Webscrapes & Crawls

Scrape content from a single page or crawl multiple pages to keep your knowledge base fresh and comprehensive. How to Add a Webscrape or Crawl:
  1. Enter the website URL.
  2. Select Scrape (single page) or Crawl (multi-page).
  3. If Crawl is selected:
    • Set Limit (max pages to crawl, e.g., 10).
    • Set Depth (how many links deep to follow).
  4. Click Add.
Supported formats: Text content from public web pages. Limits: Scrapes process a single page. Crawls can process multiple pages (max 10) based on your depth and limit settings. Processing time varies by complexity.
You can view the status, creation date, and completion date. Managing Webscrapes: Click the three dots menu on any item to:
  • View: Review the actual text content that was scraped or crawled.
  • Re-scrape / Re-crawl: Refresh the content by running the process again with the same settings.
  • Delete: Remove the entry if it’s no longer needed.

2. Documents

Upload files to enrich your knowledge base with manuals, guides, policies, and more. Supported Formats: PDF, TXT, DOC, DOCX (max 512MB per file) How to Upload:
  1. Drag and drop files or click to select
  2. Wait for upload and processing to complete
  3. Review and manage your document list
Once uploaded, you can download any document from the Knowledge Group to review or archive offline. Click the three-dot menu on any document and choose Download.
You can remove documents at any time. Processing may take a few minutes for large files.

3. FAQs

Manually add frequently asked questions to help your AI agents answer common customer queries quickly and accurately. How to Add FAQs:
  1. Click Add FAQ
  2. Enter the question and answer
  3. Save and manage your FAQ list
You can edit or delete FAQs at any time. Use the search bar to quickly find specific questions. FAQs are used on every channel a linked agent works — voice, chat, and email. An email agent answers a question that matches one of its FAQ entries straight from that entry, rather than composing an answer of its own. See Email Agents.

4. Linked Agents

See which AI agents are currently linked to this Knowledge Group. Manage connections to ensure your agents always have access to the right information. How to Manage Agents:
  • View all linked agents
  • Unlink agents as needed
Only linked agents can access the knowledge in this group. Make sure to keep your agent list up to date.

Knowledge Across Channels

Everything in a Knowledge Group — scraped web content, uploaded documents, and FAQs — is available to a linked agent on voice, on chat, and on email. An email agent answers a matching question authoritatively from the FAQ entry, and searches its linked Knowledge Groups before it writes a reply. This is new behaviour for email. Previously FAQs were honoured on voice and chat but ignored on email replies, so an email agent answered from general model knowledge, hedged, or escalated a thread even when the exact answer was sitting in its FAQ list. Nothing needs configuring. Your existing FAQ entries and Knowledge Groups start being used on the agent’s next email turn. See Email Agents.

Behaviour worth knowing

  • Email replies may be worded differently than before. Anything covered by an FAQ is now answered from that entry, so a reply that used to be composed freely will follow your FAQ wording instead — and an FAQ entry that is stale or wrong will start showing up in email replies as well as on calls and chats. Review your FAQ list before relying on it for email.
  • A long FAQ list makes each email reply cost more. The agent’s full FAQ list is included in every email reply it composes, so the longer the list, the higher the cost of each email turn. Keep FAQs to genuinely frequent questions, and move detail into documents — those are searched only when they are relevant.

Import and Export

When you export an agent, the bundle now carries its linked Knowledge Groups’ full content — name, description, every FAQ, and every URL together with its crawl settings (crawl format, crawl mode, page and depth limits, crawl-entire-domain, ignore-sitemap, and the include/exclude path lists). Previously a bundle recorded knowledge groups by name only, so importing into another workspace produced empty groups you had to rebuild by hand.
  • Within the same region, already-crawled page content and uploaded files are copied straight across rather than re-crawled, so the imported group is usable immediately.
  • Across regions, URLs are re-crawled from scratch — content can differ if the site has changed — and uploaded documents are omitted, because a file cannot be regenerated from a URL. Re-upload those manually.
The importer prefers reuse over recreation, and this catches people out. If the destination workspace already holds a Knowledge Group with the same name, that existing group is linked as-is and the bundle’s FAQs, URLs and documents are not recreated — so the imported agent answers from the destination’s content, not the source’s. Check Build → Knowledge Base after any import to confirm which group the agent is actually using.
Other outcomes you may see:
  • If the destination already holds a group whose content is identical, that group is reused and nothing is re-crawled.
  • If the destination’s copy has moved on independently, the bundle’s content is ignored and your newer content is kept.
  • If the two have genuinely diverged — or if either side’s content fingerprint is unknown — the importer creates a second, separate Knowledge Group rather than clobbering your edits, leaving two similarly named entries to reconcile by hand.
Content fingerprints are only written when a URL is freshly crawled or a file freshly uploaded, and existing data is not backfilled. So for any Knowledge Group that still contains a pre-upgrade URL or document, the fingerprint comparison cannot apply — a duplicate same-named group is a likely rather than exotic outcome. Re-crawling or re-uploading a member gives it a fingerprint.
Re-importing an updated bundle can permanently delete the older copy of that Knowledge Group — its search index and its stored files included — once no agent links it any more. If you keep an unlinked Knowledge Group as an archive, link it to an agent or export it before re-importing.
Duplicating an agent inside a single workspace is unchanged: it shares the existing Knowledge Group and none of this applies. Expect billable crawl activity when an import does re-crawl URLs.

Best Practices

  • Consolidate Knowledge Groups: It is recommended to add all knowledge documents to a single Knowledge Group. This streamlines the AI Agent’s search process and improves response times by avoiding the need to look up multiple groups.
  • Use FAQs for Common Questions: Add frequent questions directly to the FAQ section. These are processed immediately without searching through documents or web pages, resulting in faster responses for common queries.
  • Regular Updates: Keep your webscrapes and documents up to date to ensure the AI has the latest information.
  • Review Connections: Periodically check which agents are linked to ensure they have the correct access.
  • Avoid Conflicting Information: Ensure your documents do not contain contradictory facts, which can confuse the AI Agent.
  • Keep it Relevant: Only add information relevant to the specific use case. Avoid overloading the Knowledge Group with excessive or irrelevant data to maintain optimal performance.
  • Use Structured Formatting: Format documents with clear headings and bullet points. This helps the AI understand the structure and relationship of information.
  • Describe Visuals: If your documents contain charts or images, ensure the key takeaways are also written in text so the AI can read them.
  • Test After Updates: After modifying the Knowledge Group, ask your AI Agent specific questions to verify it correctly understands and uses the new material.

Troubleshooting

  • Check the URL is correct and publicly accessible
  • Some sites may block scraping or require login
  • Try again or contact support if issues persist
  • Check file format and size
  • Ensure files are not password-protected
  • Try re-uploading or use a different format
  • Ensure questions and answers are clear and concise
  • Edit or delete outdated FAQs