AI Knowledge Platform
An AI Knowledge Platform is the system that turns your documents and sites into retrievable, citable memory for assistants. In Qefro it is workspace-scoped: each AI Workspace has its own index so Support FAQs never silently merge with HR policy.
Short definition (citation-ready)
An AI Knowledge Platform ingests files and web content, chunks and indexes them (often with hybrid lexical + vector retrieval), and returns grounded passages so assistants can answer with citations inside an isolation boundary such as a workspace.
What it includes
| Capability | Role |
|---|---|
| Ingest | Uploads, crawl jobs, OCR for scans/images |
| Index | Chunking, embeddings, lexical indexes |
| Retrieve | Hybrid search at question time (Hybrid RAG) |
| Cite | Point answers back to source passages |
| Isolate | Per-workspace corpora inside a tenant |
| Govern | Delete/re-ingest, access via RBAC on Employee AI |
Architecture
Input
Sources
PDFs, docs, sites, and OCR-extracted text approved for that workspace.
Index
Workspace memory
Chunks stay inside the workspace boundary.
Output
Cited answers
Assistants ground replies in retrieved passages.
Knowledge Platform vs “upload a PDF to a chatbot”
| Chatbot upload | AI Knowledge Platform |
|---|---|
| Convenient for demos | Built for ongoing ingest and re-index |
| Often one shared pile | Workspace (and tenant) isolation |
| Citations optional | Citations as a product expectation |
| Weak ops story | APIs, jobs, delete/replace, monitoring |
How Qefro implements it
- Product page: Knowledge Platform
- Upload / manage via Admin Console and
POST /api/v1/documentsonapi.qefro.com - Retrieval powers Customer AI (widget, WhatsApp) and Employee AI (Internal Portal)
- Isolation ties to Organizations and workspaces
Workflow
Build a trustworthy knowledge workspace
- Choose the audience — Customer-safe vs internal-only corpus.
- Ingest deliberately — Prefer canonical docs over stale wiki dumps.
- Test questions — Check citations and refusal on unknown topics.
- Refresh cadence — Re-crawl or replace files when policy changes.
- Then add tools — Knowledge first; Business Actions second.
Best practices
- Separate corpora by audience (Customer AI vs Employee AI).
- Prefer fewer high-quality sources over noisy crawl-everything.
- Verify OCR quality for scans before relying on answers.
- Treat deletion and retention as security requirements, not afterthoughts.
FAQ
Is the Knowledge Platform the same as Hybrid RAG?
Hybrid RAG is the retrieval technique. The Knowledge Platform is the product system: ingest, index, isolate, retrieve, and cite.
Can two workspaces share documents?
They do not share indexes by default. Upload or crawl into each workspace that needs the content.
Does knowledge work without Business Actions?
Yes. Many deployments are knowledge-only until API tools are ready.