> ## Documentation Index > Fetch the complete documentation index at: https://docs.sigmamind.ai/llms.txt > Use this file to discover all available pages before exploring further. # Update Agent > Partially updates an existing agent by agentId. Only fields provided in the request body are updated — omitted fields remain unchanged. Returns the updated agent record. ## OpenAPI ````yaml patch /v1/agents/{agentId} openapi: 3.0.1 info: title: SigmaMind APIs description: OpenAPI documentation SigmaMind Agent Builder APIs version: '1.0' servers: - url: https://api.sigmamind.ai description: SigmaMind AI Agent Builder APIs security: - apiKeyAuth: [] tags: - name: Chats description: >- Endpoints for creating and managing text-based chat sessions with an agent. A session is started by specifying an agent and an opening message. Returns a chatId used in all subsequent get, update, completion, and end-session calls. - name: Calls description: >- Endpoints for creating and managing outbound phone calls. A call is initiated by specifying an agent, caller number, and destination number — dynamic variables can be included to personalise the agent's behaviour. Returns a callId used in all subsequent get and delete operations. - name: Phone Numbers description: >- Endpoints for managing phone numbers used in outbound and inbound calls. Supports purchasing a new number through SigmaMind or importing an existing number via SIP trunking (BYO). Each number can be assigned separate inbound and outbound agents. - name: Campaigns description: >- Endpoints for creating and managing outbound call campaigns. A campaign dials a CSV-uploaded contact list using a selected agent and caller number, with support for immediate or scheduled launch. Returns a campaignId used in all subsequent get, update, and delete operations. - name: Agents description: >- Endpoints for creating and managing single prompt agents. An agent is configured with a system prompt, voice settings, and optional tools. Returns an agentId used in all subsequent update, call, and simulation operations. - name: Integrations description: >- Endpoints for creating and managing third-party integrations (e.g. Shopify, Cal.com). An integration links your account to an external service and acts as the parent resource for auth credentials and API tools. Returns an integrationId used in all subsequent auth and tool operations. - name: Integration Auth description: >- Endpoints for managing authentication credentials for a third-party integration. Supports API Key, Basic, and Bearer token credential types — scoped to an integration and injected automatically by tools when executing. Returns an authId used in all subsequent get, update, and delete operations. - name: Integration Tools description: >- Endpoints for creating and managing API tools backed by a third-party integration. Each tool defines an HTTP endpoint, method, and parameter schema — scoped to an integration and using its stored auth credentials when executing. Returns a toolId used in all subsequent get, update, delete, and execute operations. - name: Webhooks description: >- Endpoints for registering and managing webhooks. A webhook delivers real-time event notifications via HTTP POST when selected events occur on a specific agent — each webhook is scoped to one agent and one or more event types. Payloads are signed with an HMAC secret — verify the signature on your server to confirm authenticity. - name: Test Cases description: >- Endpoints for creating and managing simulation test cases for an agent. A test case defines a conversation scenario — including user persona, goals, and expected behaviour — used to generate a synthetic conversation with the agent. Returns a testCaseId used in all subsequent get, update, delete, and batch-run operations. - name: Batch Runs description: >- Endpoints for creating and managing batch runs of simulation test cases. A batch run executes multiple test cases in parallel against a selected agent and aggregates the results for review. Returns a batchId used in all subsequent get and list test-run operations. - name: Test Runs description: >- Endpoints for retrieving test run results within a batch. Each test run represents a single test case execution within a batch run, identified by a jobId. Use batchId and agentId to scope results to the correct batch. - name: API Keys description: >- Endpoints for creating and managing API keys used to authenticate public API requests. Each key must be included in the X-API-Key request header. Returns a keyId used in all subsequent get, revoke, and delete operations. - name: QA Rules description: >- Endpoints for creating and managing quality assurance rules applied to agent conversations. A QA rule defines evaluation criteria used to automatically assess conversation quality. Returns a qaRuleId used in all subsequent get, update, and delete operations. - name: QA Issues description: >- Endpoints for retrieving and managing quality assurance issues flagged across agent conversations. A QA issue is created with status 'Fail' when a conversation violates one or more QA rules — capturing the offending rule reference. It is created with status 'Success' when the conversation passes the evaluation criteria of QA rule(s). Returns a qaIssueId used in all subsequent get operations. paths: /v1/agents/{agentId}: patch: tags: - Agents summary: Update Agent description: >- Partially updates an existing agent by agentId. Only fields provided in the request body are updated — omitted fields remain unchanged. Returns the updated agent record. operationId: updateSinglePromptAgent parameters: - name: agentId in: path description: Unique identifier of the agent to update. required: true schema: type: string example: agent_IqmljBh8eSEGAqKd requestBody: content: application/json: schema: $ref: '#/components/schemas/UpdateAgentRequest' required: true responses: '200': description: OK content: application/json: schema: $ref: '#/components/schemas/CreateAgentResponse' '400': description: Bad Request content: application/json: schema: $ref: '#/components/schemas/Error' examples: default: value: error: Bad Request message: Invalid request parameters path: /v1/agents status: 400 timestamp: '2026-05-05T10:06:46.023Z' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error' examples: default: value: error: Unauthorized message: X-API-Key is missing or invalid path: /v1/agents status: 401 timestamp: '2026-05-05T10:06:46.023Z' '403': description: Forbidden content: application/json: schema: $ref: '#/components/schemas/Error' examples: default: value: error: Forbidden message: Access denied for this resource path: /v1/agents status: 403 timestamp: '2026-05-05T10:06:46.023Z' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/Error' examples: default: value: error: Not Found message: The requested resource was not found path: /v1/agents status: 404 timestamp: '2026-05-05T10:06:46.023Z' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/Error' examples: default: value: error: Internal Server Error message: Unexpected server error path: /v1/agents status: 500 timestamp: '2026-05-05T10:06:46.023Z' components: schemas: UpdateAgentRequest: type: object description: >- Request body for updating an existing single prompt agent, including its instructions, welcome message configuration, runtime settings, and available tools. properties: agentName: type: string description: >- Human-readable name of the agent used to identify it in the dashboard and APIs. example: Auralis instructions: type: string description: >- Core system prompt that defines the agent’s behavior, personality, tone, response style, goals, and task handling logic. These instructions guide how the agent interacts with users and responds during conversations. example: >- You are a helpful customer support assistant. Answer concisely and professionally. welcomeMessageType: type: string description: >- Determines how the agent’s welcome message is generated. Use 'static' to send a fixed predefined message, or 'prompt' to dynamically generate the welcome message using AI instructions. example: static default: static enum: - static - prompt welcomeMessage: type: string description: >- The content of the welcome message. If 'welcomeMessageType' is 'static', this contains the exact message shown to the user. If it is 'prompt', this contains the prompt used to generate the welcome message dynamically. example: Welcome to our service! How can I assist you today? agentSettings: $ref: '#/components/schemas/UpdateAgentSettingsRequest' tools: type: array items: $ref: '#/components/schemas/UpdateToolRequest' CreateAgentResponse: type: object properties: agentId: type: string description: Id of the agent. example: SPIlVscbB0kkXBvZ agentName: type: string description: >- Human-readable name of the agent used to identify it in the dashboard and APIs. example: Auralis instructions: type: string description: >- Core system prompt that defines the agent’s behavior, personality, tone, response style, goals, and task handling logic. These instructions guide how the agent interacts with users and responds during conversations. example: >- You are a helpful customer support assistant. Answer concisely and professionally. welcomeMessageType: type: string description: >- Determines how the agent’s welcome message is generated. Use 'static' to send a fixed predefined message, or 'prompt' to dynamically generate the welcome message using AI instructions. example: static default: static enum: - static - prompt welcomeMessage: type: string description: >- The content of the welcome message. If 'welcomeMessageType' is 'static', this contains the exact message shown to the user. If it is 'prompt', this contains the prompt used to generate the welcome message dynamically. example: Welcome to our service! How can I assist you today? agentSettings: $ref: '#/components/schemas/CreateAgentSettingsResponse' tools: type: array items: $ref: '#/components/schemas/CreateToolResponse' Error: type: object properties: timestamp: type: string description: Error timestamp in ISO format format: date-time status: type: integer description: HTTP status code example: 400 error: type: string description: Error type or HTTP status message example: Bad Request message: type: string description: Detailed error message example: Email is required path: type: string description: Request path where error occurred example: /v1/users validationErrors: type: object description: Field validation errors (if any) example: |- { "email": "Email is required", "name": "Name is too short" } description: Standard error response UpdateAgentSettingsRequest: type: object properties: language: type: string description: The language your customers will primarily speak during calls. example: en_US default: en_US enum: - multi_nova3 - multi_nova2 - en - en_US - en_AU - en_GB - en_NZ - en_IN - hi - de - de_CH - nl - sv - sv_SE - da - da_DK - es - es_419 - fr - fr_CA - pt - pt_BR - pt_PT - it - tr - 'no' - id - bg - ca - zh - zh_CN - zh_Hans - zh_TW - zh_Hant - zh_HK - cs - et - fi - nl_BE - el - hu - ja - ko - ko_KR - lv - lt - ms - pl - ro - ru - sk - th - th_TH - uk - vi aiStartsConversation: type: boolean description: >- If true the AI agent will initiate the conversation immediately when the call connects. If false the call will connect silently, waiting for the customer to speak first before the AI responds example: true default: true backgroundSound: type: string description: Add ambient background audio during the call. example: keyboard_typing default: none enum: - keyboard_typing - office_ambience - none globalPrompt: type: string description: >- A global system prompt that is applied to every conversation to define the agent’s overall behavior, tone, and constraints. example: >- You are a professional virtual assistant. Always respond politely and keep answers concise. remindersIntervalDuration: maximum: 60 minimum: 10 type: integer description: >- Interval (in seconds) after which a follow-up reminder is automatically sent if the user does not respond. format: int32 example: 15 default: 10 remindersLimit: maximum: 10 minimum: 0 type: integer description: >- Maximum number of follow-up reminders to send when the user does not respond. Set to 0 to disable reminders. format: int32 example: 3 default: 4 endCallOnSilenceDuration: maximum: 30 exclusiveMaximum: false minimum: 0.1 exclusiveMinimum: false type: number description: >- Specifies the duration of continuous silence (in minutes) after which the call will be automatically ended. format: float example: 30 default: 5 maxCallDuration: maximum: 120 minimum: 1 type: integer description: >- Maximum call duration (in minutes) before the call is automatically terminated. format: int32 example: 40 default: 60 llmModel: type: string description: >- The language model that powers the AI's responses. To use OpenAI priority tier models, append '-fast-tier' to the model name (e.g., 'gpt-4o-mini-fast-tier'). example: gpt-4o-mini default: gpt-4o-mini enum: - gpt-5.2 - gpt-5.2-fast-tier - gpt-5.1 - gpt-5.1-fast-tier - gpt-5 - gpt-5-fast-tier - gpt-5-mini - gpt-5-mini-fast-tier - gpt-5-nano - gpt-4.1 - gpt-4.1-fast-tier - gpt-4.1-mini - gpt-4.1-mini-fast-tier - gpt-4.1-nano - gpt-4.1-nano-fast-tier - gpt-4o - gpt-4o-fast-tier - gpt-4o-mini - gpt-4o-mini-fast-tier - claude-haiku-4-5-20251001 - claude-sonnet-4-5-20250929 - claude-sonnet-4-20250514 - gemini-3.1-flash-lite-preview - gemini-3-flash-preview - gemini-2.5-flash-lite - gemini-2.5-flash llmTemperature: maximum: 1 exclusiveMaximum: false minimum: 0 exclusiveMinimum: false type: number description: >- Controls randomness in the model's output. Lower values make responses more deterministic; higher values make them more creative. If not provided, the default value is derived from the selected llmModel. format: double example: 0.5 llmTopP: maximum: 1 exclusiveMaximum: false minimum: 0 exclusiveMinimum: false type: number description: >- Controls how diverse the output is by selecting from the most probable tokens within a probability limit. Lower values make responses more focused. If not provided, the default value is derived from the selected llmModel. format: double example: 0.5 llmTopK: maximum: 200 minimum: 0 type: integer description: >- Limits token selection to the top-k most probable tokens. Lower values make output more deterministic; higher values increase variation. If not provided, the default value is derived from the selected llmModel format: int32 example: 40 voiceId: type: string description: This is the AI's speaking voice id. example: elevenlabs_SGbOfpm28edC83pZ9iGb default: elevenlabs_EXAVITQu4vr4xnSDxMaL voiceModelId: type: string description: >- Specifies the text-to-speech (TTS) model used by the agent to generate spoken audio responses. Different models may vary in voice quality, latency, language support, and naturalness. example: eleven_turbo_v2_5 default: eleven_turbo_v2_5 enum: - eleven_multilingual_v2 - eleven_flash_v2_5 - eleven_turbo_v2_5 - eleven_turbo_v2 - eleven_flash_v2 - eleven_multilingual_v1 - eleven_monolingual_v1 - tts-1 - tts-1-hd - gpt-4o-mini-tts - sonic - sonic-2 - sonic-lite - sonic-preview - sonic-turbo - arcana - mist - mistv2 - octave2_multi - inworld-tts-1 - inworld-tts-1-max ttsSpeed: maximum: 2 exclusiveMaximum: false minimum: 0.6 exclusiveMinimum: false type: number description: >- Controls the speech playback speed. Lower values make speech slower; higher values make it faster. format: double example: 0.7 ttsTemperature: maximum: 2 minimum: 0 type: number description: >- Controls variation in speech delivery. Lower values make speech more consistent; higher values add more expressiveness. format: double example: 0.5 ttsVolume: maximum: 2 exclusiveMaximum: false minimum: 0.5 exclusiveMinimum: false type: number description: >- Controls the output audio volume. Lower values make it quieter; higher values make it louder. format: double example: 0.5 default: 0 aiStartsSpeakingPlan: maximum: 1 minimum: 0 type: number description: How quickly AI starts speaking after user input. format: double example: 0.5 default: 1 aiStopsSpeakingPlan: maximum: 1 minimum: 0 type: number description: How quickly AI stops speaking when interrupted. format: double example: 0.5 default: 1 ivrHangup: type: boolean description: >- Determines whether the call should be automatically disconnected when an IVR system is detected during the call. example: true default: false agentTimezone: type: string description: >- The timezone of the agent in IANA format. Used to contextualize time-sensitive responses and scheduling. example: Asia/Kolkata default: UTC autoVolumeNormalization: type: boolean description: >- If true, it keeps the user's microphone volume consistent regardless of distance or loudness. example: true default: true backgroundNoiseFilter: type: boolean description: If true, it removes hums, buzzes, and rumbles from the audio signal. example: true default: false echoCancellation: type: boolean description: >- If true, it stops the AI's audio from looping back into the microphone. example: true default: true enablePostConversationAnalysis: type: boolean description: >- Indicates whether post-conversation analysis should be performed to extract insights after the conversation ends. example: true default: false postConversationAnalysisLlmModel: type: string description: The language model that powers the AI's post-conversation analysis. example: gpt-4o-mini default: gpt-4o-mini enum: - gpt-5.2 - gpt-5.2-fast-tier - gpt-5.1 - gpt-5.1-fast-tier - gpt-5 - gpt-5-fast-tier - gpt-5-mini - gpt-5-mini-fast-tier - gpt-5-nano - gpt-4.1 - gpt-4.1-fast-tier - gpt-4.1-mini - gpt-4.1-mini-fast-tier - gpt-4.1-nano - gpt-4.1-nano-fast-tier - gpt-4o - gpt-4o-fast-tier - gpt-4o-mini - gpt-4o-mini-fast-tier - claude-haiku-4-5-20251001 - claude-sonnet-4-5-20250929 - claude-sonnet-4-20250514 - gemini-3.1-flash-lite-preview - gemini-3-flash-preview - gemini-2.5-flash-lite - gemini-2.5-flash postConversationAnalysis: type: array description: >- List of configurations defining what insights should be extracted after the conversation ends. items: $ref: '#/components/schemas/PostConversationAnalysisRequest' webhooks: type: array description: >- List of webhook configurations that define external endpoints to be notified on specific events. items: $ref: '#/components/schemas/WebhookConfigUpdateRequest' description: >- Request body for updating an existing AI agent, including its instructions, welcome message configuration, runtime settings, and available tools. UpdateToolRequest: required: - type type: object properties: type: type: string description: >- The type determines the tool’s behavior and configuration schema, such as call transfer, variable extraction, IVR navigation, integrations, etc. nodeId: type: string description: >- The unique identifier of an existing tool within the agent. If provided, the corresponding tool will be updated. If omitted, a new tool will be created and added to the agent. toolName: type: string description: >- A unique name used to identify the tool within an agent. The name may contain only alphanumeric characters and underscores (_). If not provided, a name will be generated automatically. Tool names must be unique within the same agent. instruction: maxLength: 10000 minLength: 0 type: string description: >- Instructions that define when the agent should invoke this tool during a conversation. Use this field to describe the scenarios, user intents, or conditions under which the tool should be triggered. discriminator: propertyName: type mapping: voice_transfer_call: $ref: '#/components/schemas/VoiceTransferCallTool' extract_variables: $ref: '#/components/schemas/ExtractVariablesTool' ivr_navigator: $ref: '#/components/schemas/IvrNavigatorTool' voice_end_call: $ref: '#/components/schemas/VoiceEndCallTool' integration_tool: $ref: '#/components/schemas/IntegrationTool' oneOf: - $ref: '#/components/schemas/VoiceTransferCallTool' - $ref: '#/components/schemas/ExtractVariablesTool' - $ref: '#/components/schemas/IvrNavigatorTool' - $ref: '#/components/schemas/VoiceEndCallTool' - $ref: '#/components/schemas/IntegrationTool' CreateAgentSettingsResponse: type: object properties: language: type: string description: The language your customers will primarily speak during calls. example: en_US default: en_US aiStartsConversation: type: boolean description: >- If true the AI agent will initiate the conversation immediately when the call connects. If false the call will connect silently, waiting for the customer to speak first before the AI responds example: true default: true backgroundSound: type: string description: Add ambient background audio during the call. example: keyboard_typing default: none enum: - keyboard_typing - office_ambience - none globalPrompt: type: string description: >- A global system prompt that is applied to every conversation to define the agent’s overall behavior, tone, and constraints. example: >- You are a professional virtual assistant. Always respond politely and keep answers concise. remindersIntervalDuration: type: integer description: >- Interval (in seconds) after which a follow-up reminder is automatically sent if the user does not respond. format: int32 example: 15 default: 10 remindersLimit: type: integer description: >- Maximum number of follow-up reminders to send when the user does not respond.Set to 0 to disable reminders. format: int32 example: 3 default: 4 endCallOnSilenceDuration: type: number description: >- Specifies the duration of continuous silence (in minutes) after which the call will be automatically ended. format: float example: 30 default: 5 maxCallDuration: type: integer description: >- Maximum call duration (in minutes) before the call is automatically terminated. format: int32 example: 40 default: 60 llmModel: type: string description: The language model that powers the AI's responses. example: gpt-4o-mini default: gpt-4o-mini llmTemperature: type: number description: >- Controls randomness in the model's output. Lower values make responses more deterministic; higher values make them more creative. If not provided, the default value is derived from the selected llmModel. format: double example: 0.5 llmTopP: type: number description: >- Controls how diverse the output is by selecting from the most probable tokens within a probability limit. Lower values make responses more focused. If not provided, the default value is derived from the selected llmModel. format: double example: 0.5 llmTopK: type: integer description: >- Limits token selection to the top-k most probable tokens. Lower values make output more deterministic; higher values increase variation. If not provided, the default value is derived from the selected llmModel format: int32 example: 40 voiceId: type: string description: This is the AIs speaking voice id. example: elevenlabs_SGbOfpm28edC83pZ9iGb default: elevenlabs_EXAVITQu4vr4xnSDxMaL voiceModelId: type: string description: This is the AIs text to speech engine version. example: eleven_turbo_v2_5 default: eleven_turbo_v2_5 ttsSpeed: type: number description: >- Controls the speech playback speed. Lower values make speech slower; higher values make it faster. If not provided, the default value is derived from the selected voiceModel. format: double example: 0.7 ttsTemperature: type: number description: >- Controls variation in speech delivery. Lower values make speech more consistent; higher values add more expressiveness. If not provided, the default value is derived from the selected voiceModel. format: double example: 0.5 ttsVolume: type: number description: >- Controls the output audio volume. Lower values make it quieter; higher values make it louder. If not provided, the default value is derived from the selected voiceModel. format: double example: 0.5 aiStartsSpeakingPlan: type: number description: How quickly AI starts speaking after user input. format: double example: 0.5 default: 1 aiStopsSpeakingPlan: type: number description: How quickly AI stops speaking when interrupted. format: double example: 0.5 default: 1 ivrHangup: type: boolean description: >- Indicates whether post-conversation analysis should be performed to extract insights after the conversation ends. example: true default: false agentTimezone: type: string description: >- The timezone of the agent in IANA format. Used to contextualize time-sensitive responses and scheduling. example: Asia/Kolkata default: UTC autoVolumeNormalization: type: boolean description: >- If true, it keeps the user's microphone volume consistent regardless of distance or loudness. example: true default: true backgroundNoiseFilter: type: boolean description: If true, it removes hums, buzzes, and rumbles from the audio signal. example: true default: false echoCancellation: type: boolean description: >- If true, it stops the AI's audio from looping back into the microphone. example: true default: true enablePostConversationAnalysis: type: boolean description: >- Indicates whether post-conversation analysis should be performed to extract insights after the conversation ends. example: true default: false postConversationAnalysisLlmModel: type: string description: The language model that powers the AI's post-conversation analysis. example: gpt-4o-mini default: gpt-4o-mini postConversationAnalysis: type: array description: >- List of configurations defining what insights should be extracted after the conversation ends. items: $ref: '#/components/schemas/PostConversationAnalysisRequest' webhooks: type: array description: >- List of webhook configurations that define external endpoints to be notified on specific events. items: $ref: '#/components/schemas/WebhookConfigResponse' description: >- Configuration settings that define the agent’s runtime behavior, including voice, llm model and other operational settings. CreateToolResponse: type: object properties: type: type: string description: >- The type determines the tool’s behavior and configuration schema, such as call transfer, variable extraction, IVR navigation, integrations, etc. nodeId: type: string description: The unique identifier of the tool within the agent. toolName: type: string description: >- A unique name used to identify the tool within an agent. Use this name to reference the tool within the agent. instruction: type: string description: >- Instructions that define when the agent should invoke this tool during a conversation. Use this field to describe the scenarios, user intents, or conditions under which the tool should be triggered. discriminator: propertyName: type mapping: voice_transfer_call: $ref: '#/components/schemas/VoiceTransferCallToolResponse' extract_variables: $ref: '#/components/schemas/ExtractVariablesToolResponse' ivr_navigator: $ref: '#/components/schemas/IvrNavigatorToolResponse' voice_end_call: $ref: '#/components/schemas/VoiceEndCallToolResponse' integration_tool: $ref: '#/components/schemas/IntegrationToolAgentResponse' oneOf: - $ref: '#/components/schemas/VoiceTransferCallToolResponse' - $ref: '#/components/schemas/ExtractVariablesToolResponse' - $ref: '#/components/schemas/IvrNavigatorToolResponse' - $ref: '#/components/schemas/VoiceEndCallToolResponse' - $ref: '#/components/schemas/IntegrationToolAgentResponse' PostConversationAnalysisRequest: required: - dataType - insightInstructions - insightName type: object properties: insightName: type: string description: >- A Unique name of the insight that will be generated from the conversation. example: conversation summary insightInstructions: type: string description: >- Instructions or prompt that define how the insight should be generated from the conversation. dataType: type: string description: Defines the expected data type of the generated insight result. example: string enum: - string - boolean - number - selector options: type: array description: >- List of allowed selectable values. Required only when dataType is selector. example: - Interested - Not Interested - Follow Up Later items: type: string example: '["Interested","Not Interested","Follow Up Later"]' description: >- List of configurations defining what insights should be extracted after the conversation ends. WebhookConfigUpdateRequest: required: - events - name - url type: object properties: webhookId: type: string description: A unique identifier for the webhook. example: wh_BUbkx3PsbzQm5V10 name: type: string description: >- Human-readable name for this webhook. Used to identify it in listings and dashboards. Does not need to be unique, but a descriptive name helps distinguish multiple webhooks on the same agent. example: Call Events - Production url: pattern: https?://.+ type: string description: >- HTTPS endpoint that will receive event payloads as HTTP POST requests. Must be publicly reachable. The system expects an HTTP 2xx response within the configured timeout to confirm delivery. Non-2xx responses or timeouts are treated as delivery failures. example: https://yourapp.com/webhooks/sigmamind events: uniqueItems: true type: array description: >- Set of event types that will trigger a delivery to this webhook. 'conversation_started' fires when an agent session begins. 'conversation_ended' fires when a session closes. 'conversation_analysed' fires when post-call analysis is complete. At least one event must be specified. Only events in this set will be sent — all others are silently ignored. example: - conversation_started - conversation_ended items: type: string enum: - conversation_started - conversation_ended - conversation_analysed description: >- List of webhook configurations that define external endpoints to be notified on specific events. VoiceTransferCallTool: required: - transferTo - type type: object description: Transfers the active voice call to another number properties: type: type: string example: voice_transfer_call enum: - voice_transfer_call instruction: type: string description: >- Instructions that define when the agent should invoke this tool during a conversation. Use this field to describe the scenarios, user intents, or conditions under which the tool should be triggered. transferToRouting: type: string description: >- Defines how the destination for the call transfer is determined. Use 'static' to always transfer to a fixed phone number. Use 'dynamic' to determine the destination at runtime based on conditions or extracted variables (e.g., user intent such as OPD, radiology, etc.). example: static default: static enum: - static - dynamic transferTo: type: string description: >- Destination for the call transfer. If transferToRouting is 'static', provide a valid E.164 formatted phone number. If transferToRouting is 'dynamic', provide instructions or a dynamic variable placeholder to resolve the destination at runtime. For example: If the user wants to connect with OPD, transfer to {{dynamic_variable}} or a specific number. If the user wants to connect with radiology, transfer to {{dynamic_variable}} or a specific number. example: +9187788XXXXX extensionNumber: pattern: ^[0-9]{1,10}$|^\{\{.+\}\}$ type: string description: >- Optional extension number to dial after the call is transferred. This is typically used in IVR systems to reach a specific department or user. example: '1234' transferSettings: $ref: '#/components/schemas/TransferSettings' ExtractVariablesTool: required: - type - variables type: object description: Extracts and stores named variables from the conversation properties: type: type: string example: extract_variables enum: - extract_variables instruction: type: string description: >- Instructions that define when the agent should invoke this tool during a conversation. Use this field to describe the scenarios, user intents, or conditions under which the tool should be triggered. variables: type: array description: List of variables to extract from the conversation items: $ref: '#/components/schemas/Variable' IvrNavigatorTool: required: - type type: object description: This tool is used to navigate through IVR. properties: type: type: string example: ivr_navigator enum: - ivr_navigator instruction: type: string description: >- Instructions that define when the agent should invoke this tool during a conversation. Use this field to describe the scenarios, user intents, or conditions under which the tool should be triggered. ivrStartsConversation: type: boolean description: >- Indicates whether the call is initiated by an IVR (Interactive Voice Response) system. Set to true when the interaction begins with an automated IVR prompt before connecting to an agent or system flow. example: true default: true pauseDelay: maximum: 30000 minimum: 500 type: integer description: >- Specifies the duration (in milliseconds) to wait before assuming the IVR system has finished its input or prompt. This delay helps ensure that subsequent actions are triggered only after the IVR interaction is complete. format: int64 example: 4000 default: 2000 VoiceEndCallTool: required: - type type: object description: Ends the current voice call properties: type: type: string example: voice_end_call enum: - voice_end_call instruction: type: string description: >- Instructions that define when the agent should invoke this tool during a conversation. Use this field to describe the scenarios, user intents, or conditions under which the tool should be triggered. IntegrationTool: required: - toolId - type type: object description: Triggers an action from a connected app (e.g. Shopify, HubSpot) properties: type: type: string description: Type of the tool example: integration_tool enum: - integration_tool instruction: type: string description: >- Instructions that define when the agent should invoke this tool during a conversation. Use this field to describe the scenarios, user intents, or conditions under which the tool should be triggered. toolId: type: string description: toolId of the specific integration tool to execute example: tool_0QqvBhLiudhHyMDC speakWhileWaiting: type: boolean description: >- If enabled, the agent will provide filler or holding speech while waiting for the tool to respond. example: true default: true placeholders: type: object additionalProperties: type: string description: >- Defines values for the placeholders expected by the integration tool. Each key represents a placeholder name and its value can either be a static value or a dynamic variable using the format {{variable_name}} to inject runtime data. description: >- Defines values for the placeholders expected by the integration tool. Each key represents a placeholder name and its value can either be a static value or a dynamic variable using the format {{variable_name}} to inject runtime data. mapVariables: type: object additionalProperties: type: string description: >- Maps the response paths of the tool to dynamic variables. Each key is the variable name and the value is the mapped response path. description: >- Maps the response paths of the tool to dynamic variables. Each key is the variable name and the value is the mapped response path. WebhookConfigResponse: type: object properties: webhookId: type: string description: A unique identifier for the webhook. example: wh_BUbkx3PsbzQm5V10 name: type: string description: >- Human-readable name for this webhook. Used to identify it in listings and dashboards. Does not need to be unique, but a descriptive name helps distinguish multiple webhooks on the same agent. example: My Webhook url: pattern: https?://.+ type: string description: >- HTTPS endpoint that will receive event payloads as HTTP POST requests. Must be publicly reachable. The system expects an HTTP 2xx response within the configured timeout to confirm delivery. Non-2xx responses or timeouts are treated as delivery failures. example: https://example.com/webhook secret: type: string description: >- Secret key used to authenticate webhook payloads. This key should be securely stored and verified on the receiving server. example: mK9vXq2pL8nR5tY1wA3sD6fH0jC4bE7u events: type: array description: >- Set of event types that will trigger a delivery to this webhook. 'conversation_started' fires when an agent session begins. 'conversation_ended' fires when a session closes. 'conversation_analysed' fires when post-call analysis is complete. At least one event must be specified. Only events in this set will be sent — all others are silently ignored. items: type: string description: >- List of webhook configurations that define external endpoints to be notified on specific events. VoiceTransferCallToolResponse: type: object properties: type: type: string example: voice_transfer_call enum: - voice_transfer_call nodeId: type: string description: The unique identifier of the tool within the agent. toolName: type: string description: >- A unique name used to identify the tool within an agent. Use this name to reference the tool within the agent. instruction: type: string description: >- Instructions that define when the agent should invoke this tool during a conversation. Use this field to describe the scenarios, user intents, or conditions under which the tool should be triggered. transferToRouting: type: string description: >- Defines how the destination for the call transfer is determined. Use 'static' to always transfer to a fixed phone number. Use 'dynamic' to determine the destination at runtime based on conditions or extracted variables (e.g., user intent such as OPD, radiology, etc.). example: static default: static enum: - static - dynamic transferTo: type: string description: >- Destination for the call transfer. If transferToRouting is 'static', provide a valid E.164 formatted phone number. If transferToRouting is 'dynamic', provide instructions or a dynamic variable placeholder to resolve the destination at runtime. For example: If the user wants to connect with OPD, transfer to {{dynamic_variable}} or a specific number. If the user wants to connect with radiology, transfer to {{dynamic_variable}} or a specific number. example: +9187788XXXXX extensionNumber: type: string description: >- Optional extension number to dial after the call is transferred. This is typically used in IVR systems to reach a specific department or user. example: '1234' transferSettings: $ref: '#/components/schemas/TransferSettings' description: Transfers the active voice call to another number ExtractVariablesToolResponse: type: object properties: type: type: string example: extract_variables enum: - extract_variables nodeId: type: string description: The unique identifier of the tool within the agent. toolName: type: string description: >- A unique name used to identify the tool within an agent. Use this name to reference the tool within the agent. instruction: type: string description: >- Instructions that define when the agent should invoke this tool during a conversation. Use this field to describe the scenarios, user intents, or conditions under which the tool should be triggered. variables: type: array description: List of variables to extract from the conversation items: $ref: '#/components/schemas/Variable' description: Extracts and stores named variables from the conversation IvrNavigatorToolResponse: type: object properties: type: type: string example: ivr_navigator enum: - ivr_navigator nodeId: type: string description: The unique identifier of the tool within the agent. toolName: type: string description: >- A unique name used to identify the tool within an agent. Use this name to reference the tool within the agent. instruction: type: string description: >- Instructions that define when the agent should invoke this tool during a conversation. Use this field to describe the scenarios, user intents, or conditions under which the tool should be triggered. ivrStartsConversation: type: boolean description: >- Indicates whether the call is initiated by an IVR (Interactive Voice Response) system. Set to true when the interaction begins with an automated IVR prompt before connecting to an agent or system flow. example: true default: true pauseDelay: maximum: 30000 minimum: 500 type: integer description: >- Specifies the duration (in milliseconds) to wait before assuming the IVR system has finished its input or prompt. This delay helps ensure that subsequent actions are triggered only after the IVR interaction is complete. format: int64 example: 4000 default: 2000 description: This tool is used to navigate through IVR. VoiceEndCallToolResponse: type: object properties: type: type: string example: voice_end_call enum: - voice_end_call nodeId: type: string description: The unique identifier of the tool within the agent. toolName: type: string description: >- A unique name used to identify the tool within an agent. Use this name to reference the tool within the agent. instruction: type: string description: >- Instructions that define when the agent should invoke this tool during a conversation. Use this field to describe the scenarios, user intents, or conditions under which the tool should be triggered. description: Ends the current voice call IntegrationToolAgentResponse: type: object properties: type: type: string description: Type of the tool example: integration_tool enum: - integration_tool nodeId: type: string description: The unique identifier of the tool within the agent. toolName: type: string description: >- A unique name used to identify the tool within an agent. Use this name to reference the tool within the agent. instruction: type: string description: >- Instructions that define when the agent should invoke this tool during a conversation. Use this field to describe the scenarios, user intents, or conditions under which the tool should be triggered. toolId: type: string description: The specific tool to execute example: tool_0QqvBhLiudhHyMDC speakWhileWaiting: type: boolean description: >- If enabled, the agent will provide filler or holding speech while waiting for the tool to respond example: true default: true placeholders: type: object additionalProperties: type: string description: >- Defines values for the placeholders expected by the integration tool. Each key represents a placeholder name and its value can either be a static value or a dynamic variable using the format {{variable_name}} to inject runtime data. description: >- Defines values for the placeholders expected by the integration tool. Each key represents a placeholder name and its value can either be a static value or a dynamic variable using the format {{variable_name}} to inject runtime data. mapVariables: type: object additionalProperties: type: string description: >- Maps the response paths of the tool to dynamic variables. Each key is the variable name and the value is the mapped response path description: >- Maps the response paths of the tool to dynamic variables. Each key is the variable name and the value is the mapped response path description: Triggers an action from a connected app (e.g. Shopify, HubSpot) TransferSettings: required: - transferType type: object properties: transferType: type: string description: >- Type of transfer to perform. 'warm' keeps the current agent connected during the transfer, while 'cold' disconnects the agent immediately after initiating the transfer. enum: - warm - cold default: warm ringingDuration: maximum: 60 minimum: 25 type: integer description: >- Specifies the maximum duration (in seconds) to wait for the call to be answered. format: int32 example: 40 default: 30 waitForParticipantAnswer: type: boolean description: If true, agent will wait for the new participant to answer the call. default: true enableWhisperMessage: type: boolean description: >- If true, a whisper message will be played privately to the destination participant before the caller is connected. default: true whisperMessage: type: string description: >- The content of the whisper message. Its interpretation depends on whisperMessageType. If the type is 'static', this text is played directly. If the type is 'prompt', the text is treated as a prompt that the system uses to dynamically generate the whisper message. whisperMessageType: type: string description: >- Defines how the whisperMessage should be interpreted. 'static' means the message is used as-is, while 'prompt' means the message is treated as a prompt for generating the final whisper message. default: static enum: - static - prompt enableThreeWayMessage: type: boolean description: >- If true, a message will be delivered once the call becomes a three-way conversation between the caller, the current agent, and the destination participant. default: true threeWayMessage: type: string description: >- The content of the message delivered during the three-way connection. Its interpretation depends on threeWayMessageType. If 'static', the message is used directly. If 'prompt', it is treated as a prompt for generating the final message. threeWayMessageType: type: string description: >- Defines how the threeWayMessage should be interpreted. 'static' means the message is used as-is, while 'prompt' means the message is treated as a prompt for generating the final message. default: static enum: - static - prompt customHeaders: type: object description: Send custom header key and values along with call transfer. additionalProperties: oneOf: - type: string - type: number - type: boolean - type: object - type: array description: Configuration for the call transfer behaviour Variable: required: - description - variableName type: object properties: variableName: type: string description: Name of the variable example: customer_name dataType: type: string description: Data type of the variable to be extracted. example: dateTimeIso8601 enum: - text - boolean - number - dateTimeIso8601 description: type: string description: Description of what this variable represents description: >- Defines a variable to be extracted from a conversation, including its name, data type, and description. securitySchemes: apiKeyAuth: type: apiKey description: >- Authenticate every request by passing your API key in the `X-API-Key` header. To get your key, go to Dashboard → API Keys and create or copy your Production API key. name: X-API-Key in: header ````