The Knowledge Base is the central content store that powers your AI assistant's responses. It holds two types of items — Q&A pairs, which you author in the console or which the platform imports or generates from a file uploaded to a Q&A-type content pack, and document chunks that the platform extracts from uploaded files — and gives curators a unified workspace to search, filter, edit, rate, and govern every entry across the entire tenant.
The Knowledge Base page in Text Search mode, with the seeded Employee Handbook entries visible.
Key Concepts
- Q&A pairs — questions and answers. Each pair has a question (what the user might ask) and an answer (what the assistant should respond with). Pairs reach the Knowledge Base by three routes: authored manually with Add Q&A, imported row-by-row from a CSV or XLSX file uploaded to a Q&A-type content pack, or generated by the platform from any other supported file (PDF, DOCX, PPTX, images) uploaded to a Q&A-type pack. Imported and generated pairs are created as Draft.
- Document chunks — when you upload a file (PDF, DOCX, XLSX, etc.) to a document-type content pack, the system splits it into chunks. Each chunk contains a portion of the document with its page numbers and section heading. The same file uploaded to a Q&A-type pack produces Q&A pairs instead.
- Content packs — containers that group Q&A pairs or document chunks together. Most items belong to a pack, but a Q&A can be saved without one.
- Status workflow — items move through statuses that control visibility: Draft (hidden from users), Approved (live), Needs Attention (flagged for review), and Discarded (soft-deleted). Only Approved items are in the search index, so a new Q&A — which starts as Draft — is invisible to the assistant until you approve it.
- Search index — the runtime indexes Q&A and document content separately. The Sync Index action rebuilds both indexes so curator changes become available to the assistant.
Search Modes
The toolbar exposes two search modes via a toggle on the left of the search field. Switch between them by clicking the magnifying-glass icon (Text Search) or the sparkles icon (AI Search).
The search-mode toggle, the AI search input, and the Sync Index / Sync Status actions.
Text Search
Text Search is the default mode. As you type in the search field, results filter in real time across the question, answer, title, and chunk content fields. Combine it with the Filters popover to narrow by tag, item type, status, sensitivity, and rating, and to change the sort order.
Active filters other than Item Type appear as chips beneath the toolbar, where you can clear them individually. Item Type has no chip — reset it from inside the Filters popover, either by setting Type back to All or by clicking Clear All, which lives inside the popover and resets every filter at once.
AI Search
AI Search runs a hybrid keyword-plus-vector semantic search across the entire tenant knowledge base. Use it when you cannot remember the exact wording of an item, want to find paraphrased duplicates, or need to discover items by intent rather than by keyword.
AI Search returns ranked semantic matches with confidence labels, highlighting query terms in the title and preview.
Each result card shows:
- A type badge (Q&A or Document) with an icon
- A confidence chip combining the qualitative label (Low / Medium / High) and the normalized score percentage
- The current status of the underlying item
- For document chunks, the chunk position within the source file (
Chunk 3/12) - The title and content preview with highlighted query terms
- An optional caption generated by the search service
The result list is sorted by normalized score: semantic reranker scores are scaled to the full 0–100% range while keyword-only fallbacks are capped part-way up it, so a strong meaning-based hit appears above a coincidental keyword match. The colored bar on the left of every card mirrors the confidence level so you can scan a busy result set quickly.
AI Search only ever finds Approved items. It queries the search index, and anything that is not Approved — every Draft, Needs Attention, and Discarded item — is deliberately kept out of that index. So AI Search cannot be used to review unapproved content, and a Q&A missing from the results is far more likely to be unapproved than absent. To find items in any status, use Text Search with the Status filter.
Running an AI Search
Switch to AI Search
Click the sparkles icon in the search-mode toggle. The query field updates to the AI Search variant with a "Search semantically across the entire knowledge base" placeholder.
Type a natural-language query
Enter a question, paraphrase, or topic — anything from a single keyword to a full sentence. The query field accepts up to 500 characters.
Run the search
Press Enter or click the arrow button on the right of the field. A loading indicator replaces the arrow while the search runs; the response usually arrives within a couple of seconds.
Open a result
Click any Q&A card to open it in the details modal where you can edit, change status, or review history.
Document chunk hits are read-only in the result list. Clicking one does not open a preview — it shows a "Document hits are preview-only" notice. To edit the underlying chunk, switch to Text Search and find the parent document.
Advanced Filters
Click Filters in the toolbar to open the filter panel. The panel opens in both search modes, but not every filter is applied in both — see the warning below.
The filters popover lets you narrow results by tag, item type, status, sensitivity, rating, and sort order.
| Filter | Options |
|---|---|
| Tags | Multi-select from a fixed built-in list. Matches items carrying any of the selected tags. Q&A pairs only |
| Item Type | All, QnA, Document |
| Status | All, Approved, Needs Attention, Draft, Discarded |
| Sensitivity | All, Public, Standard, Sensitive, Secret. Q&A pairs only |
| Rating | All, 5 stars through 1 star. Matches items rated exactly that number of stars — a "4★" filter does not include 5★ items. Q&A pairs only |
| Sort | Relevance, Newest, Oldest. "Relevance" sorts by most-recently-updated, identical to "Newest" |
In AI Search, only Status and Item Type are applied. The Filters popover still offers Tags, Sensitivity, Rating and Sort in AI Search mode, and their chips still render, but those four selections never reach the semantic search — they narrow Text Search results only. Changing any filter while in AI Search also does not re-run the query: press Enter (or the arrow button) again to run it with the new Status or Item Type.
Even Status has little room to work in AI Search: the search index holds only Approved items, so filtering AI Search by Draft, Needs Attention or Discarded returns nothing. Use Text Search to review unapproved content.
Tags, Sensitivity and Rating apply to Q&A pairs only. In Text Search, selecting any of them narrows the result set to Q&As — every document chunk is excluded, even when Item Type is set to All, and even though chunk cards display a "Public" sensitivity badge and an empty 5-star rating (those are placeholder values the console paints; chunks carry no tags, sensitivity or rating). Combining one of them with Item Type = Document therefore always returns an empty result set.
"Relevance" is not a relevance ranking. In Text Search it sorts by most-recently-updated, exactly like "Newest" — the backend sorts results only by created_at or updated_at and never scores them for relevance. Only AI Search ranks results by semantic relevance, and it ignores this Sort setting entirely.
The tag vocabulary is a fixed built-in list — it is not derived from the tags in your tenant, so a tag you invented on an item will not appear as a filter option.
Creating a Q&A Item
Open the Add Dialog
Click Add Q&A in the top-right corner of the Knowledge Base page.
The Add Q&A dialog with fields for question, answer, and content pack selection.
Enter the Question and Answer
Type the question your users might ask in the Question field and the response the assistant should provide in the Answer field. Both fields are required.
(Optional) Select a Content Pack
Choose a content pack from the Content Pack dropdown. Only Q&A-type packs appear in this list. You can leave this empty — Create is enabled as soon as the question and answer are filled in — but an unfiled Q&A is harder to find and to manage in bulk, so pick a pack unless you have a reason not to.
Create the Item
Click Create. The item is saved with Draft status. A success notification appears and the dialog closes automatically.
The item is not searchable yet. A draft is excluded from the index, so the assistant cannot use it. Open the new item, click Approve, then click Save to publish it. In the details modal the quick-action buttons only stage the status change (the footer shows "You have unsaved changes"); closing without saving discards it. To publish in one click instead, use the card's three-dot menu — that writes the change immediately.
Write questions in natural language that matches how your users actually ask. For example, use "How do I request time off?" rather than "Time Off Request Procedure."
Viewing and Editing Items
Click any card — a Q&A pair or a document chunk — to open the details modal. The modal exposes two tabs at the top:
- Details — the editable view with status and sensitivity badges, quick-action buttons (Approve, Flag for Attention, Discard), inline-editable question and answer fields, rating, tags, and metadata.
- History — a chronological list of every prior version. The Compare button (enabled once two or more versions exist) opens a side-by-side diff view where you can pick a base version and a comparison target to inspect exactly what changed and who changed it.
For document chunks, the modal includes chunk navigation buttons (Previous / Next) to step through all chunks from the same source file, with a "Chunk N of Total" indicator.
Save your changes before navigating between chunks: the Previous / Next buttons are disabled while you have unsaved edits. Switching tabs is not blocked, so it is possible to move from Details to History with unsaved edits still pending — save first.
Changing an Item's Status
There are two ways to move an item through the workflow:
- From the card — open the three-dot menu on any card (Q&A pairs and document chunks both have one) and choose Approve, Discard, or Flag as Needs Attention. The change saves immediately.
- From the details modal — open the item and use the quick-action buttons (Approve, Flag for Attention, Discard). These buttons only stage the new status in the open modal; you must click Save to persist it. If you close the modal without saving, the staged status change is discarded.
Approving is what publishes an item: a draft is not in the search index, so the assistant cannot retrieve it until the item is approved and the change is saved.
Deleting an Item
Open the item's details modal and click Delete at the bottom-left. The item is deleted the moment you click — there is no confirmation prompt and no undo. This is a hard delete, distinct from the Discarded status, which only hides the item from users and can be reversed.
Delete has no confirmation step. Unlike closing the modal with unsaved edits — which raises a discard-changes dialog — clicking Delete removes the Q&A item or document chunk immediately and permanently. Export your content first if you need a backup.
Syncing the Search Index
After making changes to knowledge items, click Sync Index in the toolbar to rebuild the search and vector indexes. This ensures both Text Search and AI Search return up-to-date results, and that the runtime assistant sees the latest content.
To monitor a sync that is already in flight or review past sync runs, click Sync Status to navigate to the Sync Status page on the Knowledge Packs section. Each sync operation records its trigger source, duration, and outcome.
Uploading Files
Files are uploaded through Knowledge Packs. What the platform produces from a file depends on the type of the pack you upload it to.
Uploading to a Document-Type Pack
When you upload a file to a document-type knowledge pack, the system automatically:
- Parses the file content (supported formats: PDF, DOCX, PPTX, XLSX, PNG, JPG, TIFF, BMP).
- Splits the content into semantic chunks with page numbers and section headings.
- Creates individual document chunk items in the Knowledge Base, each created Approved.
Each chunk can then be reviewed, edited, approved, or discarded independently.
Uploading to a Q&A-Type Pack
A file uploaded to a Q&A-type pack becomes Q&A pairs, not document chunks. There are two paths:
- CSV or XLSX — imported directly, row by row, into question/answer pairs. Document parsing is skipped entirely.
- Any other supported file (PDF, DOCX, PPTX, images) — parsed and chunked like a document, after which the platform generates Q&A pairs from the chunks.
Both paths create the pairs with Draft status, so nothing they produce is in the search index until you review and approve it.
Uploads are rejected outright above 200 MB. Processing then applies a second ceiling of its own (MAX_UPLOAD_SIZE_BYTES, 100 MB unless your deployment raises it), so a file between that ceiling and 200 MB uploads successfully but fails during processing — check with your platform administrator before uploading very large files. CSV files are accepted by Q&A-type content packs only; every other supported format (PDF, DOCX, PPTX, XLSX, PNG, JPG, TIFF, BMP) is accepted by both pack types.
Field Reference
Q&A Item Fields
| Field | Description | Required |
|---|---|---|
| Question | The question users might ask | Yes |
| Answer | The response the assistant provides | Yes |
| Content Pack | Which collection this item belongs to. Optional — a Q&A saved without one is simply unfiled | No |
| Status | Controls visibility: Approved (live), Draft (hidden), Needs Attention (flagged), Discarded (removed). New Q&As start as Draft and are not searchable until approved | Set on create |
| Sensitivity | Access level: Public, Standard, Sensitive, or Secret | No (defaults to Public) |
| Rating | Curator quality assessment from 1 to 5 stars | No (defaults to 0) |
| Tags | Categorization labels chosen from a fixed built-in list | No |
Document Chunk Fields
| Field | Description | Editable |
|---|---|---|
| Title | Document filename (without extension) | Yes |
| Content | The text content of this chunk | Yes |
| Chunk Index | Position within the source document (e.g., Chunk 3 of 12) | No |
| Status | Same status workflow as Q&A items. Chunks are created Approved | Yes |
Page numbers and section headings are captured during parsing and kept on the record, but the console does not display them today.
AI Search Result Fields
| Field | Description |
|---|---|
| Type | Q&A or Document — controls which icon and color the badge uses |
| Confidence | Normalized score from 0 to 100% with a qualitative label (Low / Medium / High) |
| Status | Current lifecycle status of the underlying item |
| Chunk position | For document hits, the chunk index and total count from the source file |
| Title | The Q&A question or the document title, with query terms highlighted |
| Preview | The first ~3 lines of the answer or chunk content, with query terms highlighted |
| Caption | Optional extractive caption produced by the semantic reranker |
Related Pages
- Knowledge Packs — create content pack containers and upload documents
- Guardrails — set safety policies that evaluate user input
- Conversation Logs — see how the assistant uses knowledge items in responses
- Confidence Thresholds — tune the minimum scores the runtime accepts before answering from a knowledge item