> ## Documentation Index > Fetch the complete documentation index at: https://old-docs.you.com/llms.txt > Use this file to discover all available pages before exploring further. # Advanced Agent (Beta) ## Description This endpoint engages advanced agents that use tools, multi-turn reasoning, and planning to solve complex queries. The agents break down each query into a workflow, execute the steps iteratively, and reflect on the findings before generating a final response. ## OpenAPI ````yaml openapi_agents_advanced POST /v1/agents/runs openapi: 3.1.0 info: title: Streaming description: Streaming service for You.com version: 0.1.0 servers: - url: https://api.you.com security: - bearerAuth: [] paths: /v1/agents/runs: post: requestBody: required: true content: application/json: schema: type: object required: - agent - input properties: agent: type: string description: >- The agent mode that will be used to execute your request. This parameter must be set as 'advanced'. default: advanced input: type: string description: The input for the agent. This can be a query or a prompt. example: >- You are a biologist studying the impacts of microplastics. Explain what microplastics are to a group of engineers, explain the impacts of microplastics on the body, and what the common source and dosage of microplastics are. High-light what a safe dosage might be and how to achieve it stream: description: >- When set to "true", it will enable SSE (server side events) response. This is useful if you want to stream the response to your applications (e.g., with chatbots). Currently, only "true" is supported. type: boolean default: true tools: type: array description: >- Add tools the system can call to expand its capabilities, providing more precise answers to the input query. See [Research Tool](/tools/research-tool) and [Compute Tool](/tools/compute-tool) for more details. items: type: object properties: type: type: string enum: - research - compute verbosity: description: >- Controls the level of detail provided by the agent's response. Choosing `high` maps to a long-form report while `medium` maps to a medium verbosity report that captures most details but less comprehensive type: string enum: - medium - high default: medium workflow_config: description: >- Manages the parameters that control how the agent orchestrates and executes the workflow to answer your query. Adjust its settings to balance between response quality, thoroughness, and speed. type: object properties: max_workflow_steps: description: >- Defines the maximum number of steps the agent uses in its workflow plan to answer your query. Higher values allow for more tool calls, but it takes longer for the agent to provide the response. For instance, setting `max_workflow_steps=5` could allow the agent to call the research tool 3 times and the compute tool 2 times. type: integer minimum: 1 maximum: 20 default: 10 example: agent: advanced input: >- You are a biologist studying the impacts of microplastics. Explain what microplastics are to a group of engineers, explain the impacts of microplastics on the body, and what the common source and dosage of microplastics are. High-light what a safe dosage might be and how to achieve it responses: '200': description: Inference response in application/json or text/event-stream format. content: application/json: schema: type: object properties: output: type: array items: type: object properties: type: type: string description: The type of the output. example: chat_node.answer text: type: string description: The text of the output. example: >- What Engineers Need to Know. **Key Takeaway:** Microplastics are tiny plastic particles that are pervasive in the environment and can enter the human body through various [...] content: type: object description: Returns the exact search query. example: >- You are a biologist studying the impacts of microplastics. Explain what microplastics are to a group of engineers, explain the impacts of microplastics on the body, and what the common source and dosage of microplastics are. High-light what a safe dosage might be and how to achieve it agent: type: string description: The agent used to generate the response. default: advanced text/event-stream: schema: type: object properties: id: type: integer description: Sequence number of the SSE event, starts from 0. example: 0 event: type: string description: The type of the SSE event. example: response.output_item.added data: type: object properties: seq_id: type: integer description: >- Sequence number of the SSE event, starts from 0. Same as `id` field. example: 0 type: type: string description: The type of the SSE event. Same as `event` field. example: response.output_item.added response: type: object properties: type: type: string description: The type of the response. example: web_search.results, chat_node.answer output_index: type: integer description: The index of the output in the response. example: 0 delta: type: string description: The delta of the response. full: type: object description: The full response object of the output item. '400': description: Bad Request. Invalid or malformed request body/parameters. content: application/json: schema: type: object required: - errors properties: errors: type: array items: type: object required: - status - code - title - detail properties: status: type: string example: '400' code: type: string example: bad_request title: type: string example: Invalid request body detail: type: string example: The field 'tools' must be an array of objects. example: errors: - status: '400' code: bad_request title: Invalid request body detail: The field 'tools' must be an array of objects. '401': description: Unauthorized. Problems with API key. content: application/json: schema: type: object required: - errors properties: errors: type: array items: type: object required: - status - code - title - detail properties: status: type: string example: '401' code: type: string example: unauthorized title: type: string example: Unauthorized detail: type: string example: >- Missing or invalid Authorization header. Use 'Authorization: Bearer '. example: errors: - status: '401' code: unauthorized title: Unauthorized detail: >- Missing or invalid Authorization header. Use 'Authorization: Bearer '. '403': description: Forbidden. API key lacks scope for this path. content: application/json: schema: type: object required: - errors properties: errors: type: array items: type: object required: - status - code - title - detail properties: status: type: string example: '403' code: type: string example: tool_not_allowed title: type: string example: Tool not allowed detail: type: string example: >- You are not allowed to use the requested tool for this agent or tenant. example: errors: - status: '403' code: tool_not_allowed title: Tool not allowed detail: >- You are not allowed to use the requested tool for this agent or tenant. security: - bearerAuth: [] components: securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: API Key description: >- The unique API Key required to authorize API access. Learn how to get yours in the [“Get your API key” section of the documentation](/get-started/quickstart#get-your-api-key). ````