> ## Documentation Index > Fetch the complete documentation index at: https://docs.sixtyfour.ai/llms.txt > Use this file to discover all available pages before exploring further. # Start an investigation > Research a subject into a new Atlas investigation. The investigation is created and returned immediately, so its workspace and graph can be read while the run is still going. It is stamped with the calling credential's team, which is what decides who else can see it. ## OpenAPI ````yaml https://api.sixtyfour.ai/openapi.json post /v1/atlas/investigations openapi: 3.1.0 info: title: Sixtyfour API description: >- Intelligence API for People and Entities. Deploy AI agents that investigate, resolve identities, map relationships, and surface risk signals contact: name: Sixtyfour url: https://sixtyfour.ai/ email: support@sixtyfour.ai license: name: Proprietary version: 1.0.0 servers: - url: https://api.sixtyfour.ai description: Production security: [] tags: - name: Enrichment description: Find and enrich emails, phones, and LinkedIn for people and companies. - name: org-chart description: Discover people inside a company and build org charts. - name: Search description: Run deep and filter searches over Sixtyfour's data. - name: Workflow description: Create, run, and manage enrichment workflows. - name: Workflow Schedules description: Create and manage recurring schedules for workflows. - name: Account description: Manage and inspect your account and credit balance. - name: Intelligence description: Verify identity attributes such as age using high-tier OSINT research. - name: Atlas description: >- Read your Atlas investigations: attribution graph, workspace files, reports, and exports. paths: /v1/atlas/investigations: post: tags: - Atlas summary: Start an investigation description: >- Research a subject into a new Atlas investigation. The investigation is created and returned immediately, so its workspace and graph can be read while the run is still going. It is stamped with the calling credential's team, which is what decides who else can see it. operationId: start_investigation_v1_atlas_investigations_post parameters: - name: x-api-key in: header required: false schema: anyOf: - type: string - type: 'null' title: X-Api-Key requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/StartInvestigationRequest' responses: '202': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/RunStarted' '400': description: Request was rejected by the route's validation rules. content: application/json: schema: type: object properties: detail: type: string example: detail: Invalid request body '401': description: Missing or invalid API key. content: application/json: schema: type: object properties: detail: type: string example: detail: Invalid API key '402': description: >- Insufficient credits or no active subscription for this organization. content: application/json: schema: type: object properties: detail: type: string example: detail: Insufficient API credits '403': description: Organization access is locked. content: application/json: schema: type: object properties: detail: type: string example: detail: >- This organization no longer has access to Sixtyfour. Contact your representative at Sixtyfour. '422': description: Request body failed validation. content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' '429': description: Rate limit exceeded. content: application/json: schema: type: object properties: detail: type: string example: detail: Rate limit exceeded '500': description: Unexpected server error. Retry with backoff. content: application/json: schema: type: object properties: detail: type: string example: detail: Internal server error '503': description: >- The API key could not be checked, or the request could not be started, because a backing service is briefly unavailable. Nothing was charged. Retry after the `Retry-After` header. content: application/json: schema: type: object properties: detail: type: string example: detail: Could not verify the API key right now. Retry shortly. components: schemas: StartInvestigationRequest: properties: engine: type: string enum: - xhigh - scout title: Engine description: >- Research engine. `GET /v1/atlas/access` reports which ones this organization may run, and what each costs. default: xhigh research_plan: anyOf: - type: string - type: 'null' title: Research Plan description: Direction for this run. On a continue, what to look into next. struct: anyOf: - additionalProperties: true type: object - type: 'null' title: Struct description: >- Optional output schema. Atlas researches open-endedly into the workspace either way. relentless: type: boolean title: Relentless description: >- Research until the budget runs out (the Atlas default). Set false to let a run with `struct` stop once every field is answered, charging the turns it used (at least one unit). default: true max_credits: anyOf: - type: integer - type: 'null' title: Max Credits description: >- How much research to buy, in credits (default: one unit of the engine price), up to 10 units. On xhigh every 250 credits buy 800 team turns, used in full unless the research stops yielding: 300 buys 960. Scout researches alone, and every 50 credits buy its 100 turns. max_minutes: anyOf: - type: integer maximum: 1440 minimum: 10 - type: 'null' title: Max Minutes description: >- The longest the run may research, in minutes of working time: waits to retry a model call or an attempt do not count. When it is reached the run writes up what it found and completes, charging the credits its turns used, rounded up to the next 50, instead of the whole budget. Writing up can take a few minutes past the limit. Default: no limit. dispatch_id: anyOf: - type: string maxLength: 128 minLength: 8 - type: 'null' title: Dispatch Id description: >- Client-generated idempotency key. Reusing the same key for the same organization returns the existing run instead of starting and billing a duplicate, so a lost response is safe to retry. lead_info: additionalProperties: true type: object title: Lead Info description: 'Who to investigate, e.g. {"name": "Jane Doe", "company": "Acme"}.' name: anyOf: - type: string - type: 'null' title: Name description: Title for the investigation. Derived from lead_info when unset. private: type: boolean title: Private description: >- Visible only to you, not your team. Needs a signed-in user and a team that allows private runs. default: false type: object required: - lead_info title: StartInvestigationRequest RunStarted: properties: task_id: type: string title: Task Id description: Poll with `GET /job-status/{job_id}`. status: type: string title: Status investigation: $ref: '#/components/schemas/InvestigationReference' description: >- The investigation this run writes into. Readable through the routes below while the run is still going. type: object required: - task_id - status - investigation title: RunStarted HTTPValidationError: title: HTTPValidationError type: object properties: detail: type: array items: $ref: '#/components/schemas/ValidationError' example: detail: - loc: - body - target_company - domain msg: Field required type: missing input: null ctx: {} InvestigationReference: properties: id: type: string title: Id description: Atlas investigation ID. workspace_url: type: string maxLength: 2083 minLength: 1 format: uri title: Workspace Url description: Canonical Sixtyfour app URL for the investigation's Atlas workspace. type: object required: - id - workspace_url title: InvestigationReference description: >- Stable identity and app link carried across xhigh lifecycle responses. Live workspace statistics stay on the Atlas resource endpoints so polling a job never fans out into file, graph, or event count queries. ValidationError: title: ValidationError type: object required: - loc - msg - type properties: loc: type: array items: oneOf: - type: string - type: integer description: Path to the field that failed validation. example: - body - target_company - domain msg: type: string description: Human-readable error message. example: Field required type: type: string description: Error code (e.g. 'missing', 'value_error'). example: missing input: description: The offending input value (any type, may be null). nullable: true example: null ctx: type: object description: Optional error context. additionalProperties: true example: {} ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.