Blocks
Stagehand Agent
Autonomous web browsing agent
Use Stagehand to create an autonomous web browsing agent that can navigate across websites, perform tasks, and return structured data.
Block Preview
Stagehand Agent
Autonomous web browsing agent
Usage
- Add the block to your workflow and connect it to the upstream step.
- Configure any required credentials or tokens in the inputs.
- Fill in required inputs and optional parameters for the run.
- Run a test execution, inspect outputs, and iterate before deploying.
- Deploy the stagehand_agent block with monitoring enabled in production.
Inputs (UI)
Starting URL
short-inputPlaceholder: Enter the starting URL for the agent
Layout: full
Task
long-inputPlaceholder: Enter the task or goal for the agent to achieve. Reference variables using %key% syntax.
Layout: full
Variables
tableLayout: full
Anthropic API Key
short-inputPlaceholder: Enter your Anthropic API key
Layout: full
Output Schema
codePlaceholder: Enter JSON Schema...
Layout: full
Enable Memory
switchLayout: half
Memory Limit
sliderLayout: half
Condition: memoryEnabled = true
Importance Threshold
sliderLayout: half
Condition: memoryEnabled = true
Memory Tags
short-inputPlaceholder: customer-support, billing, technical
Layout: half
Condition: memoryEnabled = true
Inputs (API)
startUrl
stringRequired
task
stringRequired
variables
jsonOptional
apiKey
stringRequired
outputSchema
jsonOptional
memoryEnabled
booleanOptional
memoryLimit
numberOptional
memoryImportance
numberOptional
memoryTags
stringOptional
Outputs
Primary response type:
{
"agentResult": "json",
"structuredOutput": "json"
}