Skip to main content

Knowledge Base

Route: /org/knowledgebase Permission: View Knowledge Base Articles and Categories — or View Project Trainings Adding and deleting sources needs Add, Edit, and Delete Knowledge Base Articles and Categories.


1. What this actually is​

This is not the customer-facing help centre

Despite the name, this screen manages AI training sources: documents you ingest so that ticket deflection, the assistant and AI workflows can answer from your own material.

The help articles your customers read at /support/kb are a different thing entirely, authored under Settings → Knowledge Base. Two screens, two purposes, one name.

The shared permission with VOX (View Project Trainings) is the clue: the same ingested corpus feeds the voice agent.

This screenSettings → Knowledge Base
AudienceMachines — AI retrievalHumans — customers reading
ContentWhole documents you uploadArticles you write
UnitChunks for embeddingArticles and categories
Published toThe AI layer, and VOX/support/kb (HELP_006, HELP_004)
Formatting matters?No — only extractable textYes

The page states its purpose: "Manage articles, FAQs, and documentation to deflect tickets and guide AI workflows."


2. How training sources spread across the application​

A source ingested here is answerable material everywhere the AI layer reaches — which is the reason to curate rather than dump.


3. The screen​

Figure 1 — Ingested sources, with the chunk count each produced.
ColumnMeaning
Source nameThe document's title, with an extract of its opening text beneath
TypeWhat was ingested — e.g. PDF Document
ChunksHow many segments the document was split into for retrieval
StatusActive once ingestion completed and the source is searchable
Added onIngestion date
ActionsDelete — removes the source and its chunks from retrieval

Search sources… filters the list. + Train Agent ingests a new document.


4. Chunks — the number to actually read​

A document is split into chunks before embedding; retrieval matches a chunk, not a whole file.

The chunk count is your ingestion health check

Check it immediately after ingesting. A long document that yields very few chunks means the text did not extract — a scanned PDF with no text layer is the usual culprit. It will sit there marked Active, contributing nothing, and you will not find out until the assistant fails to answer something you know is in the file.

Rule of thumb: if the chunk count looks low for the document's length, re-check the source.


5. Curation​

Everything here is answerable — including the wrong things

Ingesting a superseded policy or a retired runbook makes the assistant confidently wrong, which is worse than it having no answer. The AI cannot tell that a document is out of date.

Delete a source when it is retired: that removes its chunks from retrieval immediately. Treat this list as a curated corpus, not an archive.


6. Don't confuse this with…​

ScreenWhat it is
Knowledge Base (this page)AI training sources. Machine-facing
Settings → Knowledge BaseCustomer help articles, published to /support/kb
Ticket → Knowledge ArticlesArticles linked to a specific ticket
PapersDocument management. Unrelated to either
Which one do I want?
  • A customer should be able to read it → Settings → Knowledge Base
  • The assistant should be able to answer from it → this page
  • Both → do both. They are not connected; ingesting an article here does not publish it, and publishing an article there does not train anything

7. Troubleshooting​

SymptomCause
Assistant cannot answer from a document you uploadedCheck the chunk count — likely a scanned PDF with no text layer
Assistant gives outdated answersA superseded source is still ingested. Delete it
Customers cannot find an article you added hereThis screen does not publish anything. Use Settings → Knowledge Base
Source stuck without ActiveIngestion did not complete — re-add it