--- title: "Update an agent" method: PATCH path: "/v1/agents/{agentId}" tags: ["Agents"] --- # Update an agent `PATCH /v1/agents/{agentId}` ## Path parameters - `agentId` string, required ## Request body - AgentUpdateRequest - `name` string - `enabled` boolean - `provider` 'openai' | 'anthropic' | 'google' | 'mistral' | 'zavu' — LLM provider for the AI agent. - `model` string - `systemPrompt` string - `apiKey` string - `contextWindowMessages` integer - `includeContactMetadata` boolean - `maxTokens` integer, nullable - `temperature` number, nullable - `triggerOnChannels` string[] - `triggerOnMessageTypes` string[] - `voice` AgentVoiceConfig — Voice Agent configuration on a sender's AI agent. Controls how the agent behaves on inbound and outbound phone calls through Zavu's managed voice pipeline (speech recognition, the agent's LLM, and speech synthesis, with real-time interruption handling). Requires the Voice Agents feature to be enabled for your team. - `enabled` boolean, required — Whether the agent handles voice calls. When false, the sender's number is not answered by the voice agent and outbound calls are rejected. - `greeting` string — Opening line the agent speaks when the call connects. If omitted, the agent waits for the caller to speak first. - `greetings` object — Greeting per language, keyed by language code. Used when the caller's language differs from the one `greeting` is written in. - `language` string — BCP-47 language code used for both speech recognition and speech synthesis (e.g. `en`, `es`, `pt-BR`). Auto-detected from the recipient when omitted. - `model` string — Model that runs the conversation, co-located in the voice network for lowest latency. Independent of the model used for text messaging. Derived from the agent's text model when omitted. - `sttProvider` string — Speech-recognition provider. Uses the default when omitted. - `sttModel` string — Speech-recognition model. Uses the default when omitted. - `ttsProvider` string — Speech-synthesis provider. Uses the default when omitted. - `ttsVoiceId` string — Identifier of the synthesized voice that speaks. Choose from the voices available in the dashboard. Uses a neutral default when omitted. - `voiceSpeed` number — Speech rate. 1.0 is natural. Only honoured by voices that support rate control; ignored by the others. - `interruptible` boolean — Whether the caller can interrupt the agent while it is speaking (barge-in). When true, the agent stops talking as soon as the caller starts. - `maxCallDurationMinutes` integer — Hard limit on call length in minutes. The call ends automatically when reached. - `maxIdleSeconds` integer — How long the agent waits during silence before ending the call. - `recordCalls` boolean — Whether the call audio is recorded. - `voicemailAction` 'hangup' | 'leave_message' — What the agent does when an answering machine or voicemail is detected on an outbound call. - `voicemailMessage` string — Message spoken when `voicemailAction` is `leave_message`. Falls back to `greeting` when omitted. - `transferPhoneNumber` string — E.164 phone number the agent can transfer the call to. When set, the agent is given a transfer tool it can use to hand the call to a human. ## Response `200` Agent updated. - object - `agent` Agent, required — AI Agent configuration for a sender. - `id` string, required - `senderId` string, required - `name` string, required - `enabled` boolean, required — Whether the agent is active. - `provider` 'openai' | 'anthropic' | 'google' | 'mistral' | 'zavu', required — LLM provider for the AI agent. - `model` string, required — Model ID (e.g., gpt-4o-mini, claude-3-5-sonnet). - `systemPrompt` string, required — System prompt for the agent. - `contextWindowMessages` integer — Number of previous messages to include as context. - `includeContactMetadata` boolean — Whether to include contact metadata in context. - `maxTokens` integer, nullable — Maximum tokens for LLM response. - `temperature` number, nullable — LLM temperature (0-2). - `triggerOnChannels` string[] — Channels that trigger the agent. - `triggerOnMessageTypes` string[] — Message types that trigger the agent. - `stats` object - `totalInvocations` integer - `totalTokensUsed` integer - `totalCost` number — Total cost in USD. - `createdAt` string, date-time, required - `updatedAt` string, date-time, required - `voice` AgentVoiceConfig — Voice Agent configuration on a sender's AI agent. Controls how the agent behaves on inbound and outbound phone calls through Zavu's managed voice pipeline (speech recognition, the agent's LLM, and speech synthesis, with real-time interruption handling). Requires the Voice Agents feature to be enabled for your team. - `enabled` boolean, required — Whether the agent handles voice calls. When false, the sender's number is not answered by the voice agent and outbound calls are rejected. - `greeting` string — Opening line the agent speaks when the call connects. If omitted, the agent waits for the caller to speak first. - `greetings` object — Greeting per language, keyed by language code. Used when the caller's language differs from the one `greeting` is written in. - `language` string — BCP-47 language code used for both speech recognition and speech synthesis (e.g. `en`, `es`, `pt-BR`). Auto-detected from the recipient when omitted. - `model` string — Model that runs the conversation, co-located in the voice network for lowest latency. Independent of the model used for text messaging. Derived from the agent's text model when omitted. - `sttProvider` string — Speech-recognition provider. Uses the default when omitted. - `sttModel` string — Speech-recognition model. Uses the default when omitted. - `ttsProvider` string — Speech-synthesis provider. Uses the default when omitted. - `ttsVoiceId` string — Identifier of the synthesized voice that speaks. Choose from the voices available in the dashboard. Uses a neutral default when omitted. - `voiceSpeed` number — Speech rate. 1.0 is natural. Only honoured by voices that support rate control; ignored by the others. - `interruptible` boolean — Whether the caller can interrupt the agent while it is speaking (barge-in). When true, the agent stops talking as soon as the caller starts. - `maxCallDurationMinutes` integer — Hard limit on call length in minutes. The call ends automatically when reached. - `maxIdleSeconds` integer — How long the agent waits during silence before ending the call. - `recordCalls` boolean — Whether the call audio is recorded. - `voicemailAction` 'hangup' | 'leave_message' — What the agent does when an answering machine or voicemail is detected on an outbound call. - `voicemailMessage` string — Message spoken when `voicemailAction` is `leave_message`. Falls back to `greeting` when omitted. - `transferPhoneNumber` string — E.164 phone number the agent can transfer the call to. When set, the agent is given a transfer tool it can use to hand the call to a human. - `senderIds` string[] — Senders this agent answers on. An agent can serve several; `senderId` remains the primary one, for compatibility. ## Other responses - `400` — Invalid request. - `401` — Unauthorized. - `404` — Agent not found. --- [API](https://skmtc.net/zavudev/apis/zavu-unified-messaging-layer-api.md) · [All operations](https://skmtc.net/zavudev/apis/zavu-unified-messaging-layer-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/zavudev/zavu-unified-messaging-layer-api/versions/07b87b6ae707/schema)