> ## Documentation Index > Fetch the complete documentation index at: https://docs.vocily.ai/llms.txt > Use this file to discover all available pages before exploring further. # The analysis library > Every analysis group in your workspace, with its items. **Paged.** This list used to return every row in one response. It now returns 20 by default - pass `?limit=` up to 100, and `?cursor=` with the previous response's `next_cursor` for the next page. See [Pagination](/developers/api-reference#pagination). Post-call analysis extracts structured data from a conversation — a sentiment, an outcome, a lead temperature, whatever you define. Groups belong to the **workspace**, not to an agent: a group usually outlives any one agent, and several agents run the same one. An agent stores only the selection, in `analysis_group_ids`. **Default Analysis** is the platform's own group — Call Summary, User Sentiment, Outcome and Language. Every new agent is created with it attached, which is why an agent produces a summary without anyone configuring anything. Its four items cannot be renamed or reshaped; you can detach the whole group from an agent, and add items of your own. ## OpenAPI ````yaml developers/openapi.json GET /v1/custom-analysis openapi: 3.1.0 info: title: Vocily API description: >- Public REST API for Vocily. Build and configure an agent, publish a version and put it live, place outbound calls, and read back calls, chats and what the agent remembered. Authenticate with a workspace API key as a Bearer token. Some things stay in the dashboard, by design: creating an API key, buying or connecting a phone number, setting an agent's webhook URL, connecting WhatsApp and its templates, building HTTP tools, and running batch campaigns. version: v1 servers: - url: https://api.vocily.ai description: Production security: [] paths: /v1/custom-analysis: get: tags: - custom-analysis summary: Get Custom Analysis Library description: >- Every analysis group in this workspace, with the values inside it, **cursor-paginated**. In creation order — oldest first — which is what `sort_order` leaving the public contract left behind. The envelope is `data`, like every other list; it was `{"groups": […]}` for one release and `{"categories": […]}` before that. operationId: get_custom_analysis_library_v1_custom_analysis_get parameters: - name: cursor in: query required: false schema: anyOf: - type: string - type: 'null' description: >- Opaque cursor from a previous response's `next_cursor`; omit for the first page title: Cursor description: >- Opaque cursor from a previous response's `next_cursor`; omit for the first page - name: limit in: query required: false schema: type: integer maximum: 100 minimum: 1 default: 20 title: Limit description: Maximum records to return in one page. responses: '200': description: >- The workspace's analysis library, in creation order. Groups are workspace-level — an agent stores only the selection, in `analysis_group_ids`. content: application/json: schema: type: object properties: data: type: array items: type: object properties: id: type: string name: type: string description: type: string nullable: true model: type: string nullable: true temperature: type: number nullable: true max_tokens: type: integer nullable: true conditions: type: object is_default: type: boolean items: type: array items: type: object properties: id: type: string category_id: type: string name: type: string description: type: string result_format: type: string enum: - string - number - integer - boolean - array - object extraction_method: type: string enum: - ai - regex required: type: boolean constraints: type: object fields: type: array items: type: object enabled: type: boolean is_system: type: boolean created_at: type: string format: date-time updated_at: type: string format: date-time created_at: type: string format: date-time updated_at: type: string format: date-time description: The rows on this page. has_more: type: boolean description: Whether another page exists. `false` on the last. next_cursor: type: string nullable: true description: >- Pass back as `?cursor=` for the next page; `null` on the last one. **Opaque** — do not parse or construct one. A cursor from a differently sorted list is refused with `invalid_cursor` rather than silently returning page 1. required: - data - has_more example: data: - name: Default Analysis description: >- Vocily's built-in post-call analysis. Attached to every new agent; detach it from an agent that does not need it. You can reword any extraction description, switch a value off, or add your own values to this group. model: null temperature: null max_tokens: null conditions: min_messages: 4 id: 00000007-0000-4000-8000-000000000007 items: - name: Call Summary description: >- Write a short recap of this conversation in English — one to three sentences — even when the conversation happened in Hindi, Hinglish, or any other language. Cover what the caller wanted, what the agent did about it, and how the call ended. Report only what was actually said; do not speculate about intent that was never expressed. extraction_method: ai result_format: string required: false constraints: {} fields: [] enabled: true id: 0000000c-0000-4000-8000-00000000000c category_id: 00000007-0000-4000-8000-000000000007 is_system: true created_at: '2026-09-01T19:50:05.876753Z' updated_at: '2026-09-01T19:50:05.876753Z' - name: User Sentiment description: >- Score the caller's overall sentiment across the whole conversation — the caller's, never the agent's. - positive: the caller was satisfied, agreed, thanked the agent, showed interest, or got what they called for. - negative: the caller was frustrated, annoyed, complained, disputed something, repeatedly refused, or hung up unhappy. - neutral: the caller was matter-of-fact, or the exchange was purely informational, or positive and negative moments roughly balanced out. When the caller's tone shifted during the call, judge by where they ended up. When there is genuinely too little to go on, answer neutral. extraction_method: ai result_format: string required: false constraints: enum: - positive - neutral fields: [] enabled: true id: 0000000d-0000-4000-8000-00000000000d category_id: 00000007-0000-4000-8000-000000000007 is_system: true created_at: '2026-09-01T19:50:05.876753Z' updated_at: '2026-09-01T19:50:05.876753Z' is_default: true created_at: '2026-09-01T19:50:05.876753Z' updated_at: '2026-09-01T19:50:05.876753Z' - name: dafa description: asdasd model: null temperature: null max_tokens: null conditions: {} id: 0000000e-0000-4000-8000-00000000000e items: [] is_default: false created_at: '2026-09-05T20:41:06.966532Z' updated_at: '2026-09-05T20:41:06.966532Z' has_more: false next_cursor: null '401': description: Missing or invalid API key. content: application/json: schema: $ref: '#/components/schemas/ApiError' example: detail: Invalid API key code: UNAUTHORIZED '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' '429': description: Rate limit exceeded — honor `Retry-After`. content: application/json: schema: $ref: '#/components/schemas/ApiError' example: code: rate_limited security: - bearerAuth: [] components: schemas: ApiError: type: object description: >- Error envelope. `code` is derived from the HTTP status, so branch on it for the CLASS of failure; the specific reason is `detail.code`. Every public refusal carries both. properties: detail: type: object description: >- The reason. `code` is the domain reason (e.g. `call_not_found`) and `message` is a sentence safe to log. On a `422` it also carries `errors[]`, one entry per rejected field — see `HTTPValidationError`. properties: code: type: string example: call_not_found message: type: string example: Call not found required: - code - message code: type: string description: Derived from the HTTP status, not the domain reason. example: NOT_FOUND HTTPValidationError: type: object title: HTTPValidationError description: >- A request the API could not read: a field of the wrong type, out of range, missing, or one we do not accept. Same envelope as every other error. properties: detail: type: object description: >- What was wrong, as `code`, a one-line `message`, and every offending field in `errors`. required: - code - message - errors properties: code: type: string enum: - validation_error message: type: string description: >- The first problem in one line, with a count of the rest — e.g. `model.temperature: Input should be less than or equal to 2 (and 1 more)`. errors: type: array items: $ref: '#/components/schemas/ValidationError' description: >- One entry per offending field. **Every problem is reported at once**, not just the first, so a malformed body needs one round trip to fix rather than one per field. code: type: string enum: - VALIDATION_ERROR description: Derived from the HTTP status, as on every error. ValidationError: type: object title: ValidationError required: - field - message - type properties: field: type: string description: >- The offending field as a path from the root of your request — `voice.speed`, `variables[0].key`, or `query.limit` for a query parameter. **This is the field to read.** message: type: string description: What is wrong with it, in plain language. type: type: string description: >- A stable machine code for the kind of failure, e.g. `extra_forbidden` for a field we do not accept, `missing` for a required one, or `less_than_equal` for a number out of range. Switch on this rather than on `message`, which may be reworded. securitySchemes: bearerAuth: type: http scheme: bearer description: 'Your API key as a Bearer token, e.g. `Authorization: Bearer vk_…`.' ````