Update a KB entry
PATCH /api/kb-entries/{entryId}
Updates the content of an existing knowledge base entry. You can modify the question, answer, and/or topics. Only the fields you include in the request body are updated — omitted fields are left unchanged.
Authorizations
Section titled “Authorizations ”Parameters
Section titled “ Parameters ”Path Parameters
Section titled “Path Parameters ”The unique identifier of the KB entry to update.
Request Body
Section titled “Request Body ”object
Updated question text.
Example
What are your delivery times within Europe?Updated answer text.
Example
Delivery within the EU takes 3-7 business days depending on the destination country.Updated topic tags. Replaces the existing tags entirely.
Example
[ "shipping", "delivery", "europe"]Responses
Section titled “ Responses ”The KB entry was updated and the changes are effective immediately.
A knowledge base (KB) entry is a question-answer pair that the AI uses to respond to customer inquiries. Entries can be created manually, imported via the API, or proposed automatically by the learning loop after resolved conversations. Proposed entries require human approval before the AI can use them.
object
Unique identifier for the KB entry.
Example
kb1a2b3c-5678-9abc-def0-1234567890abThe tenant this entry belongs to.
Example
a0b1c2d3-4567-89ab-cdef-0123456789abThe workspace this entry is scoped to. The AI only uses entries from the workspace that matches the conversation.
Example
w1a2b3c4-5678-9abc-def0-1234567890abThe question or topic this entry addresses. This is what the AI matches against when a customer asks something.
Example
What are your delivery times to Germany?The answer the AI should use when this entry is matched. Can include specific details, links, and instructions.
Example
Standard delivery to Germany takes 3-5 business days. Express delivery (next business day) is available for an additional fee of EUR 12.50.Tags that categorize this entry. Used for filtering and to help the AI determine relevance.
Example
[ "shipping", "delivery", "germany"]How this entry was created. ‘manual’ means created by a human, ‘learning_loop’ means proposed by the AI after analyzing resolved conversations, ‘import’ means imported via the API.
Example
manualConfidence score between 0 and 1, set by the learning loop when proposing entries. Higher values indicate the AI is more confident the entry is accurate. Null for manually created entries.
Example
0.92Lifecycle status of the entry. ‘pending_review’ entries are proposed but not yet approved — the AI will not use them. ‘approved’ entries are active and used by the AI. ‘rejected’ entries were reviewed and declined. ‘archived’ entries are no longer active but kept for audit.
Example
approvedNumber of times this entry has been referenced by the AI when responding to conversations.
Example
47Timestamp of the last time the AI referenced this entry. Null if never used.
Example
2026-03-25T14:20:00.000ZTimestamp when the entry was created.
Example
2026-02-01T12:00:00.000ZTimestamp when the entry was last updated.
Example
2026-03-15T10:30:00.000ZNo KB entry exists with the given ID in the authenticated tenant.
Standard error response returned by all endpoints on failure.
object
A human-readable error message describing what went wrong.
Example
Conversation not found