AI Task
Execute AI-powered browser automation tasks using natural language with optional geotargeting. This endpoint always streams responses using Server-Sent Events (SSE).
Streaming Response:
- All responses are streamed using Server-Sent Events (
text/event-stream) - Real-time progress updates and results as they’re generated
Geotargeting:
- Optionally specify a country code for geotargeted browsing
Use Cases:
- Web scraping and data extraction
- Form filling and interaction
- Navigation and information gathering
- Multi-step web workflows
- Content analysis from web pages
Body ParametersJSONExpand Collapse
geo_target: optional object { country } Optional geotargeting parameters for proxy requests
Optional geotargeting parameters for proxy requests
Country code using ISO 3166-1 alpha-2 standard (2 letters, e.g., “US”, “GB”, “JP”). See: https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2
ReturnsExpand Collapse
AutomateEvent = object { data, event } or object { data, event } or object { data, event } or 30 moreA Server-Sent Event from /v1/automate. Typed discriminated union keyed on event.
A Server-Sent Event from /v1/automate. Typed discriminated union keyed on event.
AIGeneration object { data, event } Envelope for the “ai:generation” event from /v1/automate.
Envelope for the “ai:generation” event from /v1/automate.
data: object { finishReason, iterationId, prompt, 8 more } Event data when AI generation occurs
Event data when AI generation occurs
messages: optional array of object { content, role, providerOptions } or object { content, role, providerOptions } or object { content, role, providerOptions } or object { content, role, providerOptions }
System object { content, role, providerOptions } A system message. It can contain system information.
Note: using the “system” part of the prompt is strongly preferred to increase the resilience against prompt injection attacks, and because not all providers support several system messages.
A system message. It can contain system information.
Note: using the “system” part of the prompt is strongly preferred to increase the resilience against prompt injection attacks, and because not all providers support several system messages.
User object { content, role, providerOptions } A user message. It can contain text or a combination of text and images.
A user message. It can contain text or a combination of text and images.
content: string or array of object { text, type, providerOptions } or object { image, type, mediaType, providerOptions } or object { data, mediaType, type, 2 more } Content of a user message. It can be a string or an array of text and image parts.
Content of a user message. It can be a string or an array of text and image parts.
array of object { text, type, providerOptions } or object { image, type, mediaType, providerOptions } or object { data, mediaType, type, 2 more }
Text object { text, type, providerOptions } Text content part of a prompt. It contains a string of text.
Text content part of a prompt. It contains a string of text.
Image object { image, type, mediaType, providerOptions } Image content part of a prompt. It contains an image.
Image content part of a prompt. It contains an image.
image: string or object { buffer, byteLength, byteOffset, 2 more } or object { byteLength } or object { buffer, byteLength, byteOffset, 2 more } Image data. Can either be:
- data: a base64-encoded string, a Uint8Array, an ArrayBuffer, or a Buffer
- URL: a URL that points to the image
Image data. Can either be:
- data: a base64-encoded string, a Uint8Array, an ArrayBuffer, or a Buffer
- URL: a URL that points to the image
File object { data, mediaType, type, 2 more } File content part of a prompt. It contains a file.
File content part of a prompt. It contains a file.
data: string or object { buffer, byteLength, byteOffset, 2 more } or object { byteLength } or object { buffer, byteLength, byteOffset, 2 more } File data. Can either be:
- data: a base64-encoded string, a Uint8Array, an ArrayBuffer, or a Buffer
- URL: a URL that points to the image
File data. Can either be:
- data: a base64-encoded string, a Uint8Array, an ArrayBuffer, or a Buffer
- URL: a URL that points to the image
Assistant object { content, role, providerOptions } An assistant message. It can contain text, tool calls, or a combination of text and tool calls.
An assistant message. It can contain text, tool calls, or a combination of text and tool calls.
content: string or array of object { text, type, providerOptions } or object { data, mediaType, type, 2 more } or object { text, type, providerOptions } or 3 moreContent of an assistant message. It can be a string or an array of text, image, reasoning, redacted reasoning, and tool call parts.
Content of an assistant message. It can be a string or an array of text, image, reasoning, redacted reasoning, and tool call parts.
array of object { text, type, providerOptions } or object { data, mediaType, type, 2 more } or object { text, type, providerOptions } or 3 more
Text object { text, type, providerOptions } Text content part of a prompt. It contains a string of text.
Text content part of a prompt. It contains a string of text.
File object { data, mediaType, type, 2 more } File content part of a prompt. It contains a file.
File content part of a prompt. It contains a file.
data: string or object { buffer, byteLength, byteOffset, 2 more } or object { byteLength } or object { buffer, byteLength, byteOffset, 2 more } File data. Can either be:
- data: a base64-encoded string, a Uint8Array, an ArrayBuffer, or a Buffer
- URL: a URL that points to the image
File data. Can either be:
- data: a base64-encoded string, a Uint8Array, an ArrayBuffer, or a Buffer
- URL: a URL that points to the image
Reasoning object { text, type, providerOptions } Reasoning content part of a prompt. It contains a reasoning.
Reasoning content part of a prompt. It contains a reasoning.
ToolCall object { input, toolCallId, toolName, 3 more } Tool call content part of a prompt. It contains a tool call (usually generated by the AI model).
Tool call content part of a prompt. It contains a tool call (usually generated by the AI model).
Arguments of the tool call. This is a JSON-serializable object that matches the tool’s input schema.
ToolResult object { output, toolCallId, toolName, 2 more } Tool result content part of a prompt. It contains the result of the tool call with the matching ID.
Tool result content part of a prompt. It contains the result of the tool call with the matching ID.
output: object { type, value, providerOptions } or object { type, value, providerOptions } or object { type, providerOptions, reason } or 3 moreResult of the tool call. This is a JSON-serializable object.
Result of the tool call. This is a JSON-serializable object.
Text object { type, value, providerOptions }
Json object { type, value, providerOptions }
value: string or number or boolean or 2 moreA JSON value can be a string, number, boolean, object, array, or null. JSON values can be serialized and deserialized by the JSON.stringify and JSON.parse methods.
A JSON value can be a string, number, boolean, object, array, or null. JSON values can be serialized and deserialized by the JSON.stringify and JSON.parse methods.
ExecutionDenied object { type, providerOptions, reason }
ErrorText object { type, value, providerOptions }
ErrorJson object { type, value, providerOptions }
value: string or number or boolean or 2 moreA JSON value can be a string, number, boolean, object, array, or null. JSON values can be serialized and deserialized by the JSON.stringify and JSON.parse methods.
A JSON value can be a string, number, boolean, object, array, or null. JSON values can be serialized and deserialized by the JSON.stringify and JSON.parse methods.
Content object { type, value }
value: array of object { text, type, providerOptions } or object { data, mediaType, type } or object { data, mediaType, type, 2 more } or 6 more
Text object { text, type, providerOptions }
FileData object { data, mediaType, type, 2 more }
FileURL object { type, url, providerOptions }
FileID object { fileId, type, providerOptions }
fileId: string or map[string]ID of the file.
If you use multiple providers, you need to specify the provider specific ids using the Record option. The key is the provider name, e.g. ‘openai’ or ‘anthropic’.
ID of the file.
If you use multiple providers, you need to specify the provider specific ids using the Record option. The key is the provider name, e.g. ‘openai’ or ‘anthropic’.
ImageData object { data, mediaType, type, providerOptions }
ImageURL object { type, url, providerOptions }
ImageFileID object { fileId, type, providerOptions }
fileId: string or map[string]Image that is referenced using a provider file id.
If you use multiple providers, you need to specify the provider specific ids using the Record option. The key is the provider name, e.g. ‘openai’ or ‘anthropic’.
Image that is referenced using a provider file id.
If you use multiple providers, you need to specify the provider specific ids using the Record option. The key is the provider name, e.g. ‘openai’ or ‘anthropic’.
Tool object { content, role, providerOptions } A tool message. It contains the result of one or more tool calls.
A tool message. It contains the result of one or more tool calls.
content: array of object { output, toolCallId, toolName, 2 more } or object { approvalId, approved, type, 2 more } Content of a tool message. It is an array of tool result parts.
Content of a tool message. It is an array of tool result parts.
ToolResult object { output, toolCallId, toolName, 2 more } Tool result content part of a prompt. It contains the result of the tool call with the matching ID.
Tool result content part of a prompt. It contains the result of the tool call with the matching ID.
output: object { type, value, providerOptions } or object { type, value, providerOptions } or object { type, providerOptions, reason } or 3 moreResult of the tool call. This is a JSON-serializable object.
Result of the tool call. This is a JSON-serializable object.
Text object { type, value, providerOptions }
Json object { type, value, providerOptions }
value: string or number or boolean or 2 moreA JSON value can be a string, number, boolean, object, array, or null. JSON values can be serialized and deserialized by the JSON.stringify and JSON.parse methods.
A JSON value can be a string, number, boolean, object, array, or null. JSON values can be serialized and deserialized by the JSON.stringify and JSON.parse methods.
ExecutionDenied object { type, providerOptions, reason }
ErrorText object { type, value, providerOptions }
ErrorJson object { type, value, providerOptions }
value: string or number or boolean or 2 moreA JSON value can be a string, number, boolean, object, array, or null. JSON values can be serialized and deserialized by the JSON.stringify and JSON.parse methods.
A JSON value can be a string, number, boolean, object, array, or null. JSON values can be serialized and deserialized by the JSON.stringify and JSON.parse methods.
Content object { type, value }
value: array of object { text, type, providerOptions } or object { data, mediaType, type } or object { data, mediaType, type, 2 more } or 6 more
Text object { text, type, providerOptions }
FileData object { data, mediaType, type, 2 more }
FileURL object { type, url, providerOptions }
FileID object { fileId, type, providerOptions }
fileId: string or map[string]ID of the file.
If you use multiple providers, you need to specify the provider specific ids using the Record option. The key is the provider name, e.g. ‘openai’ or ‘anthropic’.
ID of the file.
If you use multiple providers, you need to specify the provider specific ids using the Record option. The key is the provider name, e.g. ‘openai’ or ‘anthropic’.
ImageData object { data, mediaType, type, providerOptions }
ImageURL object { type, url, providerOptions }
ImageFileID object { fileId, type, providerOptions }
fileId: string or map[string]Image that is referenced using a provider file id.
If you use multiple providers, you need to specify the provider specific ids using the Record option. The key is the provider name, e.g. ‘openai’ or ‘anthropic’.
Image that is referenced using a provider file id.
If you use multiple providers, you need to specify the provider specific ids using the Record option. The key is the provider name, e.g. ‘openai’ or ‘anthropic’.
AIGenerationError object { data, event } Envelope for the “ai:generation:error” event from /v1/automate.
Envelope for the “ai:generation:error” event from /v1/automate.
BrowserActionCompleted object { data, event } Envelope for the “browser:action_completed” event from /v1/automate.
Envelope for the “browser:action_completed” event from /v1/automate.
BrowserActionStarted object { data, event } Envelope for the “browser:action_started” event from /v1/automate.
Envelope for the “browser:action_started” event from /v1/automate.
BrowserNavigated object { data, event } Envelope for the “browser:navigated” event from /v1/automate.
Envelope for the “browser:navigated” event from /v1/automate.
BrowserReconnected object { data, event } Envelope for the “browser:reconnected” event from /v1/automate.
Envelope for the “browser:reconnected” event from /v1/automate.
BrowserScreenshotCaptured object { data, event } Envelope for the “browser:screenshot_captured” event from /v1/automate.
Envelope for the “browser:screenshot_captured” event from /v1/automate.
BrowserScreenshotCapturedImage object { data, event } Envelope for the “browser:screenshot_captured_image” event from /v1/automate.
Envelope for the “browser:screenshot_captured_image” event from /v1/automate.
CdpEndpointConnected object { data, event } Envelope for the “cdp:endpoint_connected” event from /v1/automate.
Envelope for the “cdp:endpoint_connected” event from /v1/automate.
CdpEndpointCycle object { data, event } Envelope for the “cdp:endpoint_cycle” event from /v1/automate.
Envelope for the “cdp:endpoint_cycle” event from /v1/automate.
Complete object { data, event } Envelope for the “complete” event from /v1/automate.
Envelope for the “complete” event from /v1/automate.
data: object { finalAnswer, stats, success, error } Payload for the complete stream event. Structurally identical to TaskExecutionResult from webAgent.ts — the complete event’s data is the agent’s final TaskExecutionResult, stringified onto the SSE stream.
Payload for the complete stream event. Structurally identical to TaskExecutionResult from webAgent.ts — the complete event’s data is the agent’s final TaskExecutionResult, stringified onto the SSE stream.
Error object { data, event } Envelope for the “error” event from /v1/automate.
Envelope for the “error” event from /v1/automate.
data: object { error, success } Payload for the top-level error stream event. Emitted when an uncaught error escapes the task runner. Mirrors ErrorResponse from the server package’s taskRunner.ts — kept structurally aligned so schema and runtime stay consistent. Distinct from agent-level error events like ai:generation:error and task:validation_error, which are emitted through the normal event emitter during the agent loop.
Payload for the top-level error stream event. Emitted when an uncaught error escapes the task runner. Mirrors ErrorResponse from the server package’s taskRunner.ts — kept structurally aligned so schema and runtime stay consistent. Distinct from agent-level error events like ai:generation:error and task:validation_error, which are emitted through the normal event emitter during the agent loop.
InteractiveFormDataError object { data, event } Envelope for the “interactive:form_data:error” event from /v1/automate.
Envelope for the “interactive:form_data:error” event from /v1/automate.
data: object { fieldErrors, fields, formDescription, 5 more } Event data when form validation fails and the agent re-requests data. Carries both the error context and the fields that need new values. Callers respond to this the same way as a request event.
Event data when form validation fails and the agent re-requests data. Carries both the error context and the fields that need new values. Callers respond to this the same way as a request event.
InteractiveFormDataRequest object { data, event } Envelope for the “interactive:form_data:request” event from /v1/automate.
Envelope for the “interactive:form_data:request” event from /v1/automate.
SystemDebugCompression object { data, event } Envelope for the “system:debug_compression” event from /v1/automate.
Envelope for the “system:debug_compression” event from /v1/automate.
SystemDebugMessage object { data, event } Envelope for the “system:debug_message” event from /v1/automate.
Envelope for the “system:debug_message” event from /v1/automate.
TaskMetricsIncremental object { data, event } Envelope for the “task:metrics_incremental” event from /v1/automate.
Envelope for the “task:metrics_incremental” event from /v1/automate.
TaskSetup object { data, event } Envelope for the “task:setup” event from /v1/automate.
Envelope for the “task:setup” event from /v1/automate.
TaskTraceContext object { data, event } Envelope for the “task:trace_context” event from /v1/automate.
Envelope for the “task:trace_context” event from /v1/automate.
TaskValidated object { data, event } Envelope for the “task:validated” event from /v1/automate.
Envelope for the “task:validated” event from /v1/automate.
AutomateEvent = object { data, event } or object { data, event } or object { data, event } or 30 moreA Server-Sent Event from /v1/automate. Typed discriminated union keyed on event.
A Server-Sent Event from /v1/automate. Typed discriminated union keyed on event.
AIGeneration object { data, event } Envelope for the “ai:generation” event from /v1/automate.
Envelope for the “ai:generation” event from /v1/automate.
data: object { finishReason, iterationId, prompt, 8 more } Event data when AI generation occurs
Event data when AI generation occurs
messages: optional array of object { content, role, providerOptions } or object { content, role, providerOptions } or object { content, role, providerOptions } or object { content, role, providerOptions }
System object { content, role, providerOptions } A system message. It can contain system information.
Note: using the “system” part of the prompt is strongly preferred to increase the resilience against prompt injection attacks, and because not all providers support several system messages.
A system message. It can contain system information.
Note: using the “system” part of the prompt is strongly preferred to increase the resilience against prompt injection attacks, and because not all providers support several system messages.
User object { content, role, providerOptions } A user message. It can contain text or a combination of text and images.
A user message. It can contain text or a combination of text and images.
content: string or array of object { text, type, providerOptions } or object { image, type, mediaType, providerOptions } or object { data, mediaType, type, 2 more } Content of a user message. It can be a string or an array of text and image parts.
Content of a user message. It can be a string or an array of text and image parts.
array of object { text, type, providerOptions } or object { image, type, mediaType, providerOptions } or object { data, mediaType, type, 2 more }
Text object { text, type, providerOptions } Text content part of a prompt. It contains a string of text.
Text content part of a prompt. It contains a string of text.
Image object { image, type, mediaType, providerOptions } Image content part of a prompt. It contains an image.
Image content part of a prompt. It contains an image.
image: string or object { buffer, byteLength, byteOffset, 2 more } or object { byteLength } or object { buffer, byteLength, byteOffset, 2 more } Image data. Can either be:
- data: a base64-encoded string, a Uint8Array, an ArrayBuffer, or a Buffer
- URL: a URL that points to the image
Image data. Can either be:
- data: a base64-encoded string, a Uint8Array, an ArrayBuffer, or a Buffer
- URL: a URL that points to the image
File object { data, mediaType, type, 2 more } File content part of a prompt. It contains a file.
File content part of a prompt. It contains a file.
data: string or object { buffer, byteLength, byteOffset, 2 more } or object { byteLength } or object { buffer, byteLength, byteOffset, 2 more } File data. Can either be:
- data: a base64-encoded string, a Uint8Array, an ArrayBuffer, or a Buffer
- URL: a URL that points to the image
File data. Can either be:
- data: a base64-encoded string, a Uint8Array, an ArrayBuffer, or a Buffer
- URL: a URL that points to the image
Assistant object { content, role, providerOptions } An assistant message. It can contain text, tool calls, or a combination of text and tool calls.
An assistant message. It can contain text, tool calls, or a combination of text and tool calls.
content: string or array of object { text, type, providerOptions } or object { data, mediaType, type, 2 more } or object { text, type, providerOptions } or 3 moreContent of an assistant message. It can be a string or an array of text, image, reasoning, redacted reasoning, and tool call parts.
Content of an assistant message. It can be a string or an array of text, image, reasoning, redacted reasoning, and tool call parts.
array of object { text, type, providerOptions } or object { data, mediaType, type, 2 more } or object { text, type, providerOptions } or 3 more
Text object { text, type, providerOptions } Text content part of a prompt. It contains a string of text.
Text content part of a prompt. It contains a string of text.
File object { data, mediaType, type, 2 more } File content part of a prompt. It contains a file.
File content part of a prompt. It contains a file.
data: string or object { buffer, byteLength, byteOffset, 2 more } or object { byteLength } or object { buffer, byteLength, byteOffset, 2 more } File data. Can either be:
- data: a base64-encoded string, a Uint8Array, an ArrayBuffer, or a Buffer
- URL: a URL that points to the image
File data. Can either be:
- data: a base64-encoded string, a Uint8Array, an ArrayBuffer, or a Buffer
- URL: a URL that points to the image
Reasoning object { text, type, providerOptions } Reasoning content part of a prompt. It contains a reasoning.
Reasoning content part of a prompt. It contains a reasoning.
ToolCall object { input, toolCallId, toolName, 3 more } Tool call content part of a prompt. It contains a tool call (usually generated by the AI model).
Tool call content part of a prompt. It contains a tool call (usually generated by the AI model).
Arguments of the tool call. This is a JSON-serializable object that matches the tool’s input schema.
ToolResult object { output, toolCallId, toolName, 2 more } Tool result content part of a prompt. It contains the result of the tool call with the matching ID.
Tool result content part of a prompt. It contains the result of the tool call with the matching ID.
output: object { type, value, providerOptions } or object { type, value, providerOptions } or object { type, providerOptions, reason } or 3 moreResult of the tool call. This is a JSON-serializable object.
Result of the tool call. This is a JSON-serializable object.
Text object { type, value, providerOptions }
Json object { type, value, providerOptions }
value: string or number or boolean or 2 moreA JSON value can be a string, number, boolean, object, array, or null. JSON values can be serialized and deserialized by the JSON.stringify and JSON.parse methods.
A JSON value can be a string, number, boolean, object, array, or null. JSON values can be serialized and deserialized by the JSON.stringify and JSON.parse methods.
ExecutionDenied object { type, providerOptions, reason }
ErrorText object { type, value, providerOptions }
ErrorJson object { type, value, providerOptions }
value: string or number or boolean or 2 moreA JSON value can be a string, number, boolean, object, array, or null. JSON values can be serialized and deserialized by the JSON.stringify and JSON.parse methods.
A JSON value can be a string, number, boolean, object, array, or null. JSON values can be serialized and deserialized by the JSON.stringify and JSON.parse methods.
Content object { type, value }
value: array of object { text, type, providerOptions } or object { data, mediaType, type } or object { data, mediaType, type, 2 more } or 6 more
Text object { text, type, providerOptions }
FileData object { data, mediaType, type, 2 more }
FileURL object { type, url, providerOptions }
FileID object { fileId, type, providerOptions }
fileId: string or map[string]ID of the file.
If you use multiple providers, you need to specify the provider specific ids using the Record option. The key is the provider name, e.g. ‘openai’ or ‘anthropic’.
ID of the file.
If you use multiple providers, you need to specify the provider specific ids using the Record option. The key is the provider name, e.g. ‘openai’ or ‘anthropic’.
ImageData object { data, mediaType, type, providerOptions }
ImageURL object { type, url, providerOptions }
ImageFileID object { fileId, type, providerOptions }
fileId: string or map[string]Image that is referenced using a provider file id.
If you use multiple providers, you need to specify the provider specific ids using the Record option. The key is the provider name, e.g. ‘openai’ or ‘anthropic’.
Image that is referenced using a provider file id.
If you use multiple providers, you need to specify the provider specific ids using the Record option. The key is the provider name, e.g. ‘openai’ or ‘anthropic’.
Tool object { content, role, providerOptions } A tool message. It contains the result of one or more tool calls.
A tool message. It contains the result of one or more tool calls.
content: array of object { output, toolCallId, toolName, 2 more } or object { approvalId, approved, type, 2 more } Content of a tool message. It is an array of tool result parts.
Content of a tool message. It is an array of tool result parts.
ToolResult object { output, toolCallId, toolName, 2 more } Tool result content part of a prompt. It contains the result of the tool call with the matching ID.
Tool result content part of a prompt. It contains the result of the tool call with the matching ID.
output: object { type, value, providerOptions } or object { type, value, providerOptions } or object { type, providerOptions, reason } or 3 moreResult of the tool call. This is a JSON-serializable object.
Result of the tool call. This is a JSON-serializable object.
Text object { type, value, providerOptions }
Json object { type, value, providerOptions }
value: string or number or boolean or 2 moreA JSON value can be a string, number, boolean, object, array, or null. JSON values can be serialized and deserialized by the JSON.stringify and JSON.parse methods.
A JSON value can be a string, number, boolean, object, array, or null. JSON values can be serialized and deserialized by the JSON.stringify and JSON.parse methods.
ExecutionDenied object { type, providerOptions, reason }
ErrorText object { type, value, providerOptions }
ErrorJson object { type, value, providerOptions }
value: string or number or boolean or 2 moreA JSON value can be a string, number, boolean, object, array, or null. JSON values can be serialized and deserialized by the JSON.stringify and JSON.parse methods.
A JSON value can be a string, number, boolean, object, array, or null. JSON values can be serialized and deserialized by the JSON.stringify and JSON.parse methods.
Content object { type, value }
value: array of object { text, type, providerOptions } or object { data, mediaType, type } or object { data, mediaType, type, 2 more } or 6 more
Text object { text, type, providerOptions }
FileData object { data, mediaType, type, 2 more }
FileURL object { type, url, providerOptions }
FileID object { fileId, type, providerOptions }
fileId: string or map[string]ID of the file.
If you use multiple providers, you need to specify the provider specific ids using the Record option. The key is the provider name, e.g. ‘openai’ or ‘anthropic’.
ID of the file.
If you use multiple providers, you need to specify the provider specific ids using the Record option. The key is the provider name, e.g. ‘openai’ or ‘anthropic’.
ImageData object { data, mediaType, type, providerOptions }
ImageURL object { type, url, providerOptions }
ImageFileID object { fileId, type, providerOptions }
fileId: string or map[string]Image that is referenced using a provider file id.
If you use multiple providers, you need to specify the provider specific ids using the Record option. The key is the provider name, e.g. ‘openai’ or ‘anthropic’.
Image that is referenced using a provider file id.
If you use multiple providers, you need to specify the provider specific ids using the Record option. The key is the provider name, e.g. ‘openai’ or ‘anthropic’.
AIGenerationError object { data, event } Envelope for the “ai:generation:error” event from /v1/automate.
Envelope for the “ai:generation:error” event from /v1/automate.
BrowserActionCompleted object { data, event } Envelope for the “browser:action_completed” event from /v1/automate.
Envelope for the “browser:action_completed” event from /v1/automate.
BrowserActionStarted object { data, event } Envelope for the “browser:action_started” event from /v1/automate.
Envelope for the “browser:action_started” event from /v1/automate.
BrowserNavigated object { data, event } Envelope for the “browser:navigated” event from /v1/automate.
Envelope for the “browser:navigated” event from /v1/automate.
BrowserReconnected object { data, event } Envelope for the “browser:reconnected” event from /v1/automate.
Envelope for the “browser:reconnected” event from /v1/automate.
BrowserScreenshotCaptured object { data, event } Envelope for the “browser:screenshot_captured” event from /v1/automate.
Envelope for the “browser:screenshot_captured” event from /v1/automate.
BrowserScreenshotCapturedImage object { data, event } Envelope for the “browser:screenshot_captured_image” event from /v1/automate.
Envelope for the “browser:screenshot_captured_image” event from /v1/automate.
CdpEndpointConnected object { data, event } Envelope for the “cdp:endpoint_connected” event from /v1/automate.
Envelope for the “cdp:endpoint_connected” event from /v1/automate.
CdpEndpointCycle object { data, event } Envelope for the “cdp:endpoint_cycle” event from /v1/automate.
Envelope for the “cdp:endpoint_cycle” event from /v1/automate.
Complete object { data, event } Envelope for the “complete” event from /v1/automate.
Envelope for the “complete” event from /v1/automate.
data: object { finalAnswer, stats, success, error } Payload for the complete stream event. Structurally identical to TaskExecutionResult from webAgent.ts — the complete event’s data is the agent’s final TaskExecutionResult, stringified onto the SSE stream.
Payload for the complete stream event. Structurally identical to TaskExecutionResult from webAgent.ts — the complete event’s data is the agent’s final TaskExecutionResult, stringified onto the SSE stream.
Error object { data, event } Envelope for the “error” event from /v1/automate.
Envelope for the “error” event from /v1/automate.
data: object { error, success } Payload for the top-level error stream event. Emitted when an uncaught error escapes the task runner. Mirrors ErrorResponse from the server package’s taskRunner.ts — kept structurally aligned so schema and runtime stay consistent. Distinct from agent-level error events like ai:generation:error and task:validation_error, which are emitted through the normal event emitter during the agent loop.
Payload for the top-level error stream event. Emitted when an uncaught error escapes the task runner. Mirrors ErrorResponse from the server package’s taskRunner.ts — kept structurally aligned so schema and runtime stay consistent. Distinct from agent-level error events like ai:generation:error and task:validation_error, which are emitted through the normal event emitter during the agent loop.
InteractiveFormDataError object { data, event } Envelope for the “interactive:form_data:error” event from /v1/automate.
Envelope for the “interactive:form_data:error” event from /v1/automate.
data: object { fieldErrors, fields, formDescription, 5 more } Event data when form validation fails and the agent re-requests data. Carries both the error context and the fields that need new values. Callers respond to this the same way as a request event.
Event data when form validation fails and the agent re-requests data. Carries both the error context and the fields that need new values. Callers respond to this the same way as a request event.
InteractiveFormDataRequest object { data, event } Envelope for the “interactive:form_data:request” event from /v1/automate.
Envelope for the “interactive:form_data:request” event from /v1/automate.
SystemDebugCompression object { data, event } Envelope for the “system:debug_compression” event from /v1/automate.
Envelope for the “system:debug_compression” event from /v1/automate.
SystemDebugMessage object { data, event } Envelope for the “system:debug_message” event from /v1/automate.
Envelope for the “system:debug_message” event from /v1/automate.
TaskMetricsIncremental object { data, event } Envelope for the “task:metrics_incremental” event from /v1/automate.
Envelope for the “task:metrics_incremental” event from /v1/automate.
TaskSetup object { data, event } Envelope for the “task:setup” event from /v1/automate.
Envelope for the “task:setup” event from /v1/automate.
TaskTraceContext object { data, event } Envelope for the “task:trace_context” event from /v1/automate.
Envelope for the “task:trace_context” event from /v1/automate.
TaskValidated object { data, event } Envelope for the “task:validated” event from /v1/automate.
Envelope for the “task:validated” event from /v1/automate.
AI Task
curl https://api.tabstack.ai/v1/automate \
-H 'Content-Type: application/json' \
-H "Authorization: Bearer $TABSTACK_API_KEY" \
-d "{
\"task\": \"Find the top 3 trending repositories and extract their names, descriptions, and star counts\",
\"guardrails\": \"browse and extract only, don't interact with repositories\",
\"maxIterations\": 50,
\"maxValidationAttempts\": 3,
\"url\": \"https://github.com/trending\"
}"{
"error": "maxIterations must be between 1 and 100"
}{
"error": "invalid URL format"
}{
"error": "task is required"
}Returns Examples
{
"error": "maxIterations must be between 1 and 100"
}{
"error": "invalid URL format"
}{
"error": "task is required"
}