The knowledge base is everything the agent should know about your business but is too business-specific to live in the scenario prompt. Menu items, price lists, service descriptions, opening hours, FAQ, refund policy — anything that lets the agent answer "do you have…?", "how much…?", "can I…?" correctly instead of guessing.
The platform indexes the knowledge base and the agent retrieves from it in real time during the call. The retrieval is grounded — the agent quotes from your data, it does not invent facts. When the knowledge base is silent on a question, the agent says so and either escalates or captures a lead, rather than making something up.
What you can add
Two input formats:
- Your website — paste a URL and the platform crawls the public pages, extracts readable text, and indexes it. The first crawl runs during project creation; you can re-crawl any time after.
- PDF documents — menus, datasheets, brochures, price lists. Drop the file into the Knowledge base panel. We extract text (no OCR — provide text-based PDFs, not scans). Up to 20 MB per file, with a soft cap of 50 files per project.
How indexing works (in plain language)
When you add content, the platform splits it into overlapping chunks, computes an embedding for each chunk, and stores them in a vector database. At call time, when the agent looks up "what time do you close on Sunday?", we embed the question, find the most relevant chunks, and feed them back to the agent. Everything happens inside a tight latency budget so the agent answers fast.
You do not see this machinery. You see: knowledge added, searchable in a few seconds.
Refreshing content
For websites, you can:
- Re-crawl on demand — click Refresh when you change prices or services
- Auto-refresh daily — a toggle; the platform re-fetches your site every day
- Keep it frozen — leave auto-refresh off if your business is stable
For uploaded PDFs, content stays as you uploaded it until you replace it.
Boundaries — what knowledge is for vs not for
Use the knowledge base for facts the agent should know: prices, hours, menu, locations, policies, FAQ. The agent reads these and quotes from them.
Do not use the knowledge base for rules — the rules go in the scenario goal and prompt. "Do not book parties of more than 8" is a rule; put it in the goal's constraints. "Our largest available booth seats 8 people" is a fact; put it in the knowledge base.
The distinction matters because the agent treats knowledge as quotable but treats rules as binding. Mixing them weakens both.
Multilingual knowledge
The agent answers in the caller's language regardless of what language your knowledge is written in — retrieval is meaning-based, not word-based, so a Spanish question can find the answer in your English price list. You still get the best results with first-class content in the languages most of your callers speak.
Privacy and storage
Knowledge base content is yours. The platform stores it in the EU under the same tenant isolation as the rest of your project data. Embeddings are computed via OpenAI; we never use customer data to train shared AI models. See Security.
Capacity and limits
Today's defaults, per project:
- Up to 50 files in the knowledge base (soft limit)
- Up to 20 MB per file
- A site crawl indexes up to 30 pages by default — enough for most small-business sites; raised on request for large catalogues
- Indexing time is metered as crawler usage — see Billing; small crawls are free.
If you are bumping these caps, contact support and we lift them per project. They are conservative defaults, not architectural ceilings.