---
title: "List KB Gaps"
method: GET
path: "/voice/knowledge-base/{agentId}/gaps"
tags: ["Voice Agent Intelligence"]
---

# List KB Gaps

`GET /voice/knowledge-base/{agentId}/gaps`

## Request

- Base URL: `https://api.speakai.co/v1`
- URL: `https://api.speakai.co/v1/voice/knowledge-base/{agentId}/gaps`
- Auth: API key in header `x-speakai-key` and API key in header `x-access-token`

### List Knowledge Base Gaps

Lists this agent's pending KB gaps -- questions callers asked that the agent answered with low confidence or an explicit "I don't know," surfaced automatically after calls. Up to the 50 most recent pending gaps, newest first.

## Path parameters

- `agentId` string, required

## Response `200`

OK

- object
  - `status` 'success'
  - `data` object
    - `gaps` object[]
      - `_id` string: MongoDB document id, included because every document has one; use gapId to identify it.
      - `gapId` string: Server-generated. Immutable.
      - `agentId` string
      - `query` string: The caller question that triggered a low-confidence or hedging KB answer.
      - `context` string
      - `avgRetrievalScore` number
      - `conversationId` string: The call this gap surfaced from. See Conversations.
      - `suggestedTitle` string
      - `suggestedAnswer` string: AI-drafted answer. Override with title/answer in the request body when adding to the KB.
      - `status` 'pending' | 'added' | 'dismissed'
      - `severity` 'low' | 'medium' | 'high'
      - `resolvedAt` string, date-time, nullable
      - `createdAt` string, date-time
      - `updatedAt` string, date-time

---

[API](https://skmtc.dev/speakai/apis/speak-ai-api.md) · [All operations](https://skmtc.dev/speakai/apis/speak-ai-api/llms.txt) · [OpenAPI document](https://skmtc.dev/speakai/apis/speak-ai-api/revisions/52d777e6d46e?raw)