> ## Documentation Index > Fetch the complete documentation index at: https://docs.devic.ai/llms.txt > Use this file to discover all available pages before exploring further. # Update an assistant > Updates an existing assistant with the provided data. Supports partial updates. ## OpenAPI ````yaml PATCH /v1/assistants/{identifier} openapi: 3.0.0 info: title: Devic.ai Public API description: >- Devic.ai is an AI platform that allows you to create, manage, and use AI agents for various tasks. version: 1.0.0 contact: name: Devic.ai Support url: https://devic.ai x-logo: url: https://devic.ai/logo.png altText: Devic.ai Logo x-summary: Public API for interacting with Devic.ai platform servers: - url: https://api.devic.ai description: Production server - url: https://staging-api.devic.ai description: Staging server security: - bearerAuth: [] tags: - name: Projects description: Group agents, assistants, documents and costs into projects - name: Documents description: >- Knowledge base documents: create, version, attach and index markdown content for RAG - name: Document Folders description: Organise knowledge base documents into folders and attach them in bulk - name: Files description: Upload files and obtain shareable download URLs to attach to messages - name: Agents description: Endpoints related to AI agents and their operations - name: Assistants description: Endpoints for interacting with assistants and their specializations - name: Tool Servers description: Endpoints for managing tool servers and their tool definitions - name: Health description: API health check endpoints - name: Documentation description: Endpoints for retrieving markdown documentation paths: /v1/assistants/{identifier}: patch: tags: - Assistants summary: Update an assistant description: >- Updates an existing assistant with the provided data. Supports partial updates. operationId: updateAssistant parameters: - name: identifier in: path required: true description: The unique identifier of the assistant to update schema: type: string requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/UpdateAssistantRequest' responses: '200': description: Assistant updated successfully content: application/json: schema: $ref: '#/components/schemas/AssistantDetailResponse' '400': description: Invalid request data '401': description: Unauthorized - Invalid or missing token '404': description: Assistant not found '500': description: Internal Server Error security: - bearerAuth: [] components: schemas: UpdateAssistantRequest: type: object properties: name: type: string description: Assistant name description: type: string description: Assistant description presets: type: string description: System prompt / instructions model: type: string description: Default LLM model provider: type: string description: Default LLM provider imgUrl: type: string description: Image URL for the assistant state: type: string enum: - active - inactive - coming_soon description: Assistant state availableToolsGroupsUids: type: array items: type: string description: Tool group UIDs enabledTools: type: array items: type: string description: Enabled tool names accessConfiguration: type: object properties: externalAccess: type: boolean visibilityByRole: type: array items: type: string widgetConfiguration: type: object properties: enabled: type: boolean sourcesWhiteList: type: array items: type: string color: type: string welcomeMessage: type: string memoryDocuments: type: array items: type: object structuredOutput: type: object guardrailsConfiguration: type: object properties: enabled: type: boolean guardrails: type: object codeSnippetIds: type: array items: type: string availableSkillIds: type: array items: type: string subagentsIds: type: array items: type: string maxChatMessages: type: integer maxToolResponseInputTokens: type: integer contextManagement: type: object properties: fullContextTurnDepth: type: integer description: >- Number of most-recent turns sent to the model in full; older turns are replaced by their summary. 0 or omitted disables compression. alwaysIncludeUserMessages: type: boolean description: >- When true, user messages are always sent in full regardless of depth. description: >- Context depth control: summarize older turns to reduce the token footprint sent to the model. AssistantDetailResponse: type: object properties: _id: type: string description: Assistant ID identifier: type: string description: Unique identifier name: type: string description: Assistant name description: type: string description: Assistant description presets: type: string description: System prompt / instructions model: type: string description: Default LLM model provider: type: string description: Default LLM provider imgUrl: type: string description: Image URL state: type: string description: Assistant state availableToolsGroupsUids: type: array items: type: string enabledTools: type: array items: type: string accessConfiguration: type: object widgetConfiguration: type: object memoryDocuments: type: array items: type: object structuredOutput: type: object guardrailsConfiguration: type: object codeSnippetIds: type: array items: type: string availableSkillIds: type: array items: type: string subagentsIds: type: array items: type: string maxChatMessages: type: integer maxToolResponseInputTokens: type: integer contextManagement: type: object properties: fullContextTurnDepth: type: integer description: >- Number of most-recent turns sent to the model in full; older turns are replaced by their summary. 0 or omitted disables compression. alwaysIncludeUserMessages: type: boolean description: >- When true, user messages are always sent in full regardless of depth. description: >- Context depth control: summarize older turns to reduce the token footprint sent to the model. creationTimestampMs: type: integer description: Creation timestamp in milliseconds lastEditTimestampMs: type: integer description: Last edit timestamp in milliseconds securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: JWT description: Use JWT token for authentication ````