Your content, answering questions
Upload documents, link Google Docs, or point us at your website. Your agents and MCP servers answer from that content with hybrid retrieval and inline citations — not from the model's imagination.
Every format that matters
PDF, Word, Markdown and plain text uploads, Google Docs links, and full website crawling with automatic extraction.
Hybrid retrieval
Semantic search combined with keyword matching, sentence-aware chunking and relevance floors — tuned so wrong answers get filtered, not served.
Citations by default
Answers cite the exact source passage, so your users can check the receipts.
Fresh automatically
Linked URLs re-sync on a schedule you choose — hourly on higher plans — so the agent never quotes last quarter's pricing.
Reusable libraries
Knowledge bases are workspace-level: build once, attach to any number of agents and MCP servers.
What teams build with it
Three jobs this does the day you turn it on.
Turn a website into an agent's brain
Point the crawler at your domain and a couple of minutes later the agent knows your pages, prices and policies — and keeps knowing them, on the re-sync cadence you pick.
Make a document library answerable
Drop in the PDFs and Word files nobody reads and get something your team and your customers can actually ask a question of.
One source of truth, many products
Keep the knowledge base in one place and attach it everywhere, so a policy change lands in every agent and MCP server at once.
Where you set this up
The same build screen every feature is configured from — this row is the one you would touch.
Under the hood
The details you will want before you commit.
How it works
Ingest
Drag in files, paste Google Docs links, or crawl your site.
Attach
Connect knowledge bases to any agent or MCP server in your workspace.
Trust the answers
Every response is grounded and cited; re-ingestion keeps sources current.
Where it earns its keep
Industry playbooks that lean on this piece — what to build first, and what to charge.
Frequently asked questions
No. Uploads are parsed on the server and only the extracted text is kept — the binary itself is never stored.
Linked URLs re-crawl on the cadence you choose, down to hourly on higher plans, and re-ingestion replaces the old passages rather than stacking on top of them.
Yes. Answers carry inline citations naming the source document or page, so anyone reading them can check the receipts.
Ingestion volume and re-sync frequency are what separate the plans — the pricing page carries the current numbers.
How it compares
Side by side with the tools people usually weigh this against.
SuperCognit vs Chatbase →
Chatbase is a popular no-code builder for chatbots trained on your data, aimed mostly at website support.
SuperCognit vs CustomGPT.ai →
CustomGPT.ai builds RAG chatbots from your content, with a focus on accurate, cited answers.
SuperCognit vs MyAskAI →
MyAskAI is an AI support agent trained on your help docs, positioned as a lightweight add-on to tools like Intercom and Zendesk.