> ## Documentation Index > Fetch the complete documentation index at: https://docs.trugen.ai/llms.txt > Use this file to discover all available pages before exploring further. # Update Agent > Updates an Agent with new avatar, knowledge base, or system settings. ## OpenAPI ````yaml PUT /ext/agent/{id} openapi: 3.0.3 info: title: TruGen Developer Platform API version: 1.0.0 description: OpenAPI specification for MCP endpoint servers: - url: https://api.trugen.ai/v1 security: [] paths: /ext/agent/{id}: parameters: - name: id in: path required: true schema: type: string format: uuid description: Unique identifier for the Agent put: summary: Update an existing Agent description: Updates an Agent with new avatar, knowledge base, or system settings. operationId: updateAgent requestBody: required: true content: application/json: schema: type: object properties: agent_name: type: string description: Display name of the agent. example: Customer Support Agent agent_system_prompt: type: string description: Foundational system instruction used by this agent. example: >- You are a helpful AI assistant that handles customer service inquiries. avatars: type: array description: List of avatars associated with this agent. items: type: object properties: avatar_key_id: type: string description: Avatar identifier key. example: 1e4ea106 persona_name: type: string description: Display name for the avatar persona. example: Sofia - Friendly Support persona_prompt: type: string description: Behavioral prompt for the avatar interaction style. example: >- Speak in a warm, engaging tone and provide clear answers. config: type: object description: >- Configuration for avatar behavior and runtime settings. properties: llm: type: object description: Large Language Model settings used by the avatar. properties: model: type: string description: Identifier of the LLM model. example: meta-llama/llama-4-maverick-17b-128e-instruct provider: type: string description: Provider used for LLM inference. example: groq url: type: string description: >- Custom provider URL of the LLM model. (Required if provider is 'custom') default: sample url token: type: string description: >- Custom provider API token for the LLM model. (Required if provider is 'custom') default: sample token stt: type: object description: Speech-to-Text model configuration. properties: model: type: string description: Speech recognition model identifier. example: flux-general-en provider: type: string description: STT provider service name. example: deepgram min_endpointing_delay: type: number description: Minimum endpointing delay in seconds. example: 0.3 max_endpointing_delay: type: number description: Maximum endpointing delay in seconds. example: 0.4 tts: type: object description: Text-to-Speech generation configuration. properties: model_id: type: string description: Voice synthesis model identifier. example: eleven_turbo_v2_5 provider: type: string description: TTS provider service name. example: elevenlabs voice_id: type: string description: Voice ID used to synthesize speech. example: ZUrEGyu8GFMwnHbvLhv2 callback_events: type: array description: Webhook events that should trigger callbacks. items: type: string example: utterance_committed example: - participant_left - agent.started_speaking - agent.stopped_speaking - agent.interrupted - user.started_speaking - user.stopped_speaking - utterance_committed - max_call_duration_timeout callback_url: type: string description: Webhook endpoint URL to send callback events to. example: https://webhooks.example.com/agent-events config: type: object description: Agent-level configuration properties. properties: maxCallDuration: type: integer description: Maximum call duration allowed in seconds. example: 1800 conversationalContext: type: string description: >- Context label used to maintain continuity across sessions. example: customer-support memory: type: object description: Memory configuration for the agent. properties: isEnabled: type: boolean description: Whether memory is enabled for the agent. example: false instruction: type: string description: Instruction for how the agent should utilize memory. example: >- Sample instruction for the agent to utilize memory effectively in conversations. knowledge_base: type: array description: List of knowledge bases attached to this agent. nullable: true items: type: object properties: id: type: string format: uuid description: Knowledge base identifier. example: ac79226e-73e1-41fe-8cde-469ae4e244fa name: type: string description: Name of the knowledge base. example: Product Support Articles description: type: string description: Short summary of the knowledge base content. example: >- Contains FAQs and troubleshooting guides for product lines. tool: type: array description: List of tools attached to this agent. nullable: true items: type: object properties: id: type: string format: uuid description: Tool identifier. default: ac79226e-73e1-41fe-8cde-469ae4e244fa name: type: string description: Name of the tool. default: Product Support Articles mcp: type: array description: List of MCPs attached to this agent. nullable: true items: type: object properties: id: type: string format: uuid description: MCP identifier. default: ac79226e-73e1-41fe-8cde-469ae4e244fa name: type: string description: Name of the MCP . default: Product Support Articles record: type: boolean description: Determines whether voice call recordings should be stored. example: true is_active: type: boolean description: Determines whether this record is active or not. example: true created_at: type: string format: date-time description: Timestamp indicating when the agent was created. example: '2025-12-01T10:20:30.000Z' updated_at: type: string format: date-time description: Last updated timestamp for the agent. example: '2025-12-03T14:50:00.000Z' example: id: b63c2a53-266b-4b43-a71b-7ea8b5e2e916 agent_name: Customer Support Agent agent_system_prompt: >- You are a helpful AI assistant that handles customer service inquiries. avatars: - avatar_key_id: 1e4ea106 persona_name: Sofia - Friendly Support persona_prompt: Speak in a warm, engaging tone and provide clear answers. config: llm: model: meta-llama/llama-4-maverick-17b-128e-instruct provider: groq stt: model: flux-general-en provider: deepgram min_endpointing_delay: 0.3 max_endpointing_delay: 0.4 tts: model_id: eleven_turbo_v2_5 provider: elevenlabs voice_id: ZUrEGyu8GFMwnHbvLhv2 callback_events: - participant_left - agent.started_speaking - agent.stopped_speaking - agent.interrupted - user.started_speaking - user.stopped_speaking - utterance_committed - max_call_duration_timeout callback_url: '' config: maxCallDuration: 1800 conversationalContext: customer-support memory: isEnabled: false instruction: sample memory instruction for the agent knowledge_base: - id: ac79226e-73e1-41fe-8cde-469ae4e244fa name: Product Support Articles description: Contains FAQs and troubleshooting guides for product lines. record: true is_active: true created_at: '2025-12-01T10:20:30.000Z' updated_at: '2025-12-03T14:50:00.000Z' responses: '200': description: Agent updated successfully content: application/json: schema: type: object properties: id: type: string format: uuid message: type: string example: id: 098f083e-64c3-4c84-b3af-1b3e0b2538b3 message: Agent updated successfully '400': description: Invalid request body content: application/json: schema: type: object properties: error: type: string example: error: Invalid request body '401': description: Unauthorized – missing or invalid API key content: application/json: schema: type: object properties: error: type: string example: error: 'Unauthorized: not a valid authorization api key' '404': description: Agent not found content: application/json: schema: type: object properties: error: type: string example: message: Agent details not found '500': description: Internal server error content: application/json: schema: type: object properties: error: type: string example: error: Failed to update agent security: - apiKeyAuth: [] components: securitySchemes: apiKeyAuth: type: apiKey in: header name: x-api-key ````