> ## Documentation Index > Fetch the complete documentation index at: https://docs.beam.ai/llms.txt > Use this file to discover all available pages before exploring further. # Process agent setup steps > Multi-step agent configuration endpoint. Use this after agent creation (via /agent-context and /agent-creation). **GENERATE_SOP**: Generates Standard Operating Procedures for the agent - Required: agentId, query - Returns: nextStep (GRAPH_GENERATION) **GRAPH_GENERATION**: Creates agent workflow graph - Required: agentId - Returns: nextStep (TOOL_MATCHING) **TOOL_MATCHING**: Matches existing tools to agent needs - Required: agentId - Returns: nextStep (TOOL_GENERATION) **TOOL_GENERATION**: Generates new custom tools if needed - Required: agentId - Returns: nextStep (TOOL_INTEGRATION) **TOOL_INTEGRATION**: Integrates selected tools with the agent - Required: agentId - Returns: nextStep (UPDATE_AGENT) **UPDATE_AGENT**: Finalizes and updates the agent configuration - Required: agentId - Returns: nextStep (AGENT_UPDATED) Note: Use /agent-context first to get threadId, then /agent-creation to create the agent and get agentId before using this endpoint. ## OpenAPI ````yaml post /agent-setup openapi: 3.0.0 info: title: Public API description: Public endpoints to interact with agents and orchestrate tasks version: '1.0' contact: {} servers: - url: https://api.beamstudio.ai security: [] tags: [] paths: /agent-setup: post: tags: - Agent Setup summary: Process agent setup steps description: >- Multi-step agent configuration endpoint. Use this after agent creation (via /agent-context and /agent-creation). **GENERATE_SOP**: Generates Standard Operating Procedures for the agent - Required: agentId, query - Returns: nextStep (GRAPH_GENERATION) **GRAPH_GENERATION**: Creates agent workflow graph - Required: agentId - Returns: nextStep (TOOL_MATCHING) **TOOL_MATCHING**: Matches existing tools to agent needs - Required: agentId - Returns: nextStep (TOOL_GENERATION) **TOOL_GENERATION**: Generates new custom tools if needed - Required: agentId - Returns: nextStep (TOOL_INTEGRATION) **TOOL_INTEGRATION**: Integrates selected tools with the agent - Required: agentId - Returns: nextStep (UPDATE_AGENT) **UPDATE_AGENT**: Finalizes and updates the agent configuration - Required: agentId - Returns: nextStep (AGENT_UPDATED) Note: Use /agent-context first to get threadId, then /agent-creation to create the agent and get agentId before using this endpoint. operationId: BeamAgentController_processInformation parameters: - name: current-workspace-id in: header required: true schema: type: string requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/SetupBeamAgentDTO' responses: '200': description: >- Agent setup step processed successfully. Response structure varies by step (see operation description). content: application/json: schema: $ref: '#/components/schemas/AgentSetupProcessResponseDto' '201': description: '' '400': description: >- Bad Request - Missing required fields for the current step or invalid step provided. security: - x-api-key: [] components: schemas: SetupBeamAgentDTO: type: object properties: query: type: string maxLength: 50000 description: >- User input or instructions for the current setup step. Use this to provide context about what the agent should do, describe its purpose, or give feedback during the setup process. example: >- I want to create an agent that helps users with customer support inquiries contextFileIds: description: >- Array of context file UUIDs to attach to the agent. These files provide additional knowledge or reference materials that the agent can use when processing requests. example: - a1b2c3d4-e5f6-7890-abcd-ef1234567890 - b2c3d4e5-f6a7-8901-bcde-f12345678901 type: array items: type: string format: uuid agentId: type: string format: uuid description: >- UUID of the agent. Required for all setup steps (GENERATE_SOP and onwards) to identify which agent is being configured. example: f47ac10b-58cc-4372-a567-0e02b2c3d479 agentSetupStep: enum: - GENERATE_SOP - GRAPH_GENERATION - TOOL_MATCHING - TOOL_GENERATION - TOOL_INTEGRATION - UPDATE_AGENT - AGENT_UPDATED - CREATE_TASK type: string description: >- Current step in the agent setup workflow. Use /agent-context and /agent-creation first, then use this endpoint for the remaining steps: • GENERATE_SOP - Generate Standard Operating Procedures for the agent (requires query) • GRAPH_GENERATION - Create the agent's workflow graph • TOOL_MATCHING - Match existing tools to the agent's needs • TOOL_GENERATION - Generate new custom tools if needed • TOOL_INTEGRATION - Integrate selected tools with the agent • UPDATE_AGENT - Finalize and update the agent configuration • AGENT_UPDATED - Confirmation that setup is complete example: GENERATE_SOP required: - agentId - agentSetupStep AgentSetupProcessResponseDto: type: object properties: nextStep: enum: - GENERATE_SOP - GRAPH_GENERATION - TOOL_MATCHING - TOOL_GENERATION - TOOL_INTEGRATION - UPDATE_AGENT - AGENT_UPDATED - CREATE_TASK type: string description: >- The next step in the agent setup workflow. Use this value to determine which step to call next. example: SOP_GENERATION agentResponse: description: >- Agent creation response containing the created agent details and associated context files. allOf: - $ref: '#/components/schemas/SaveAgentResponseDto' required: - nextStep - agentResponse SaveAgentResponseDto: type: object properties: agent: $ref: '#/components/schemas/Agent' contextFiles: type: array items: type: string required: - agent - contextFiles Agent: type: object properties: id: type: string description: Unique identifier for the agent. example: agent-123e4567-e89b-12d3-a456-426614174000 name: type: string description: Name of the agent. example: Customer Support Agent description: type: string description: Description of the agent. settings: description: Agent settings. allOf: - $ref: '#/components/schemas/AgentSettingDto' config: description: Agent configuration. allOf: - $ref: '#/components/schemas/AgentConfig' workspaceId: type: string description: UUID of the workspace. creatorId: type: string description: UUID of the creator. type: enum: - beam-os - user-agent - pre-configured-agent type: string description: Type of the agent. vectorDbId: type: string description: UUID of the vector database. defaultTaskId: type: string description: Default task ID. themeIconUrl: type: string description: URL of the theme icon for the agent. example: https://example.com/icons/support-agent.png agentCategoryId: type: string description: UUID of the agent category. userAccessTokenId: type: string description: UUID of the user access token. agentSetupSessionId: type: string description: UUID of the agent setup session. agentIntroMessage: type: string description: Agent introduction message. agentSetupMessage: type: string description: Agent setup message. skipAgentSetupSop: type: boolean description: Whether to skip agent setup SOP. isAttachmentDataPulledIn: type: boolean description: >- Whether attachment data from tasks should be pulled into the agent context. creditUsage: type: number description: Total credit usage for this agent. example: 12.5 order: type: number description: Display order of the agent. createdAt: format: date-time type: string updatedAt: format: date-time type: string required: - id - name - creatorId - type - vectorDbId - creditUsage - order - createdAt - updatedAt AgentSettingDto: type: object properties: prompts: description: Array of prompt templates used to guide the agent behavior. example: - You are a helpful customer support agent. - Always be polite and professional. type: array items: type: string preferredModel: type: string description: Preferred AI model for this agent. example: gpt-4 instructions: type: string description: Additional instructions for agent behavior. example: Focus on providing concise answers. required: - prompts AgentConfig: type: object properties: restrictions: type: string taskTemplates: type: array items: $ref: '#/components/schemas/AgentTaskTemplate' tools: type: array items: type: string llmTools: type: array items: type: object sop: type: object defaultTaskId: type: string workspaceId: type: string AgentTaskTemplate: type: object properties: id: type: string description: Template ID. objective: type: string description: Task objective. description: type: string description: Task description. steps: description: Steps in this task template. type: array items: $ref: '#/components/schemas/AgentTaskTemplateStep' default: type: boolean description: Whether this is the default template. category: $ref: '#/components/schemas/AgentTaskTemplateCategory' lastUpdatedAt: format: date-time type: string description: Last updated timestamp. required: - id - objective - description - steps AgentTaskTemplateStep: type: object properties: step: type: string description: Step description. toolId: type: string description: Tool ID. iconSrc: type: string description: Icon source URL. iconUrl: type: string description: Icon URL. beamTool: type: boolean description: Whether this is a Beam tool. gptTool: type: boolean description: Whether this is a GPT tool. consentRequired: type: boolean description: Whether consent is required. integrationId: type: string description: Integration ID. isIntegrationRequired: type: boolean description: Whether integration is required. isIntegrationConnected: type: boolean description: Whether integration is connected. integrationProvider: type: string description: Integration provider. integrationIdentifier: type: string description: Integration identifier. toolDetail: type: object integrationCustomAuthParameters: type: object required: - step AgentTaskTemplateCategory: type: object properties: id: type: string title: type: string securitySchemes: x-api-key: type: apiKey in: header name: x-api-key ````