Knowledge Base
Answer from your own content
Upload PDFs, paste URLs, or type text. The agent searches your knowledge base during calls and answers from your content — not hallucinated responses, but grounded answers from your source material.
RAG-Powered Search
Documents are chunked and embedded using OpenAI text-embedding-3-small. During calls, the agent retrieves the most relevant chunks via pgvector similarity search and uses them as context.
Multiple Source Types
Upload PDF documents, paste website URLs for automatic crawling, or add text snippets directly. All sources are processed into searchable chunks.
Grounded Answers
The agent cites your content. If the knowledge base doesn't contain the answer, the agent says so rather than making something up.
How It Works
Get Knowledge Base running
Create a knowledge base
Go to your agent's Knowledge Base tab. Give it a name and start adding sources.
Upload content
Add PDFs, URLs, or text. Documents are automatically chunked (512 tokens, 50-token overlap) and embedded.
Add a KB Search node
Drop a Knowledge Base Search node into your flow. When the conversation reaches that point, the agent queries your content.
Test and refine
Ask questions in the flow tester. Check which chunks are being retrieved. Adjust content or add more sources as needed.
Pricing
Pay only for what you use
Pay As You Go
$0 to start
$20 in free credits. No subscription. Pay per interaction when you need more.
- ✓Full platform access
- ✓Visual flow builder
- ✓Knowledge base & RAG
- ✓Australian phone numbers
- ✓Call transcripts & analytics
Enterprise
Custom
Dedicated infrastructure, SLA, and compliance terms for teams that need them.
- ✓Everything in Pay-as-you-go
- ✓Dedicated support
- ✓Custom MSA / DPA
- ✓SSO & role-based access
- ✓Priority SLA
FAQ
Common Questions
How large can my knowledge base be?
+How fast is the search?
+Can I update content without redeploying?
+Start building. $20 in free credits.
No card required. Build a flow, test it, put it on a real number.