Core Concepts

Skyvern has eight core concepts. Master these and you can build any browser automation.

Tasks

A Task is a single automation job—think of it as asking Skyvern to do one thing. You provide a prompt describing the goal, and Skyvern navigates the browser to complete it.

from skyvern import Skyvern

skyvern = Skyvern(api_key="YOUR_API_KEY")

result = await skyvern.run_task(
    prompt="Find the top 3 posts on the front page",
    url="https://news.ycombinator.com",
    data_extraction_schema={
        "type": "object",
        "properties": {
            "posts": {
                "type": "array",
                "items": {"type": "string"}
            }
        }
    }
)

print(result.output)  # {"posts": ["Post 1", "Post 2", "Post 3"]}

Key properties:

Property	Description
`prompt`	Natural language description of the goal (required)
`url`	Starting URL for the task
`data_extraction_schema`	JSON Schema defining expected output structure
`max_steps`	Maximum steps allowed (controls cost)
`engine`	AI model to use (see Engines below)
`browser_session_id`	Run in an existing browser session
`webhook_url`	Callback URL for async completion

Use Tasks for: one-off automations, quick data extraction, prototyping before building a workflow. When you need reusable, multi-step automations, use Workflows instead.

Workflows

A Workflow is a reusable template composed of blocks. Unlike tasks, workflows can be versioned, shared across your team, and executed repeatedly with different parameters.

Parameters: {{search_query}}, {{max_price}} Each block can reference outputs from previous blocks.

result = await skyvern.run_workflow(
    workflow_id="wpid_abc123",
    parameters={
        "search_query": "wireless headphones",
        "max_price": 100
    }
)

print(result.output)

Workflows support Jinja templating:

Reference parameters: {{search_query}}
Reference previous block outputs: {{extract_block.product_name}}

Use Workflows for: repeatable automations, multi-step processes, team-shared templates, complex logic with loops or conditionals. See Workflow Blocks for the full block reference.

Blocks

Blocks are the building units of workflows. Each block performs one specific task, and blocks execute sequentially—each can reference outputs from previous blocks.

Block	Purpose
Navigation	AI-guided navigation toward a goal—Skyvern figures out the clicks and inputs
Action	Perform a single specific action (click, type, select, upload)
Go to URL	Navigate directly to a specific URL
Login	Authenticate using stored credentials
Wait	Pause execution for a specified duration
Human Interaction	Pause for manual intervention (CAPTCHA, approval, etc.)

Data & Files

Block	Purpose
Extract	Pull structured data from a page into JSON
File Download	Download files from websites
File Upload	Upload files to form fields
File Parser	Process PDFs, CSVs, and Excel files
PDF Parser	Specialized PDF text extraction

Logic & Control Flow

Block	Purpose
Conditional	Branch workflow based on conditions (if/else)
For Loop	Repeat a sequence of blocks over a list
Validation	Assert conditions; halt workflow on failure
Code	Execute custom Python/Playwright scripts

Communication & Integration

Block	Purpose
HTTP Request	Make API calls to external services
Text Prompt	Text-only LLM prompt (no browser interaction)
Send Email	Send email messages

For detailed block configuration, see Workflow Blocks.

Runs

Every time you execute a task or workflow, Skyvern creates a Run to track progress and store outputs.

result = await skyvern.run_task(
    prompt="Extract the main heading",
    url="https://example.com"
)

print(result.run_id)   # "tsk_abc123"
print(result.status)   # "completed"
print(result.output)   # {"heading": "Welcome"}

Run identifiers:

Task runs: tsk_* prefix
Workflow runs: wr_* prefix

Run response fields:

Field	Description
`run_id`	Unique identifier
`status`	Current lifecycle state
`output`	Extracted data (matches your schema)
`recording_url`	Video of the execution
`screenshot_urls`	Screenshots captured during execution
`downloaded_files`	Files retrieved (with URLs and checksums)
`failure_reason`	Error details if failed
`step_count`	Number of steps taken

Billing: You’re billed per step. A step is one AI decision + action cycle. Use max_steps to cap costs during development.

Credentials

Credentials provide secure storage for authentication data. Skyvern encrypts credentials at rest and in transit, and injects them directly into the browser—credentials are never sent to or seen by the LLM. Supported credential types:

Usernames and passwords
TOTP codes (authenticator apps)
Credit cards

Credential sources:

Skyvern — Native encrypted storage
Bitwarden — Sync from your Bitwarden vault
1Password — Sync from your 1Password vault
Azure Key Vault — Enterprise secret management

See Credentials for setup instructions.

Browser Sessions & Profiles

Skyvern offers two ways to manage browser state across runs:

	Browser Session	Browser Profile
Lifetime	Expires after timeout (max 24h)	Persists indefinitely
Use case	Real-time task chaining	Skip login on repeated runs
Sharing	Single use	Shared across team

Browser Sessions

A live browser instance that maintains state across multiple tasks. Use sessions when you need to chain tasks in real-time or allow human intervention.

# Create a session (default: 60 minutes, max: 24 hours)
session = await skyvern.create_browser_session(timeout=120)

# Run tasks in the same session
await skyvern.run_task(
    prompt="Log in with the test account",
    url="https://example.com/login",
    browser_session_id=session.browser_session_id
)

# Second task reuses the authenticated state
await skyvern.run_task(
    prompt="Extract the account balance",
    url="https://example.com/dashboard",
    browser_session_id=session.browser_session_id
)

# Clean up
await skyvern.close_browser_session(
    browser_session_id=session.browser_session_id
)

Session limits: 5 to 1,440 minutes (24 hours max). Default: 60 minutes.

Browser Profiles

A saved snapshot of browser state. Unlike sessions, profiles persist indefinitely and can be reused across days or weeks—perfect for skipping login on repeated runs.

# Create a profile from a completed run
profile = await skyvern.create_browser_profile(
    name="my-authenticated-profile",
    workflow_run_id=run.run_id
)

# Future runs restore the authenticated state
await skyvern.run_workflow(
    workflow_id="wpid_extract_data",
    browser_profile_id=profile.browser_profile_id
)

What’s saved: Cookies, authentication tokens, local storage, session storage. See Browser Sessions for details.

Artifacts

Every run generates artifacts for observability, debugging, and audit trails.

result = await skyvern.run_task(
    prompt="Download the quarterly report",
    url="https://example.com"
)

print(result.recording_url)      # Full video of execution
print(result.screenshot_urls)    # List of screenshot URLs
print(result.downloaded_files)   # [{"url": "...", "checksum": "..."}]

Artifact	Description
Recordings	End-to-end video of the entire run
Screenshots	Captured after each action
Downloaded files	Files retrieved during execution
Logs	JSON-structured logs at step, task, and workflow levels
HAR files	HTTP Archive data for network debugging

In the Skyvern UI, go to Runs → click a run → view the Actions and Recording tabs.

Engines

Skyvern supports multiple AI engines for task execution:

Engine	Description
`skyvern-2.0`	Latest Skyvern model (default, recommended)
`skyvern-1.0`	Previous Skyvern model
`openai-cua`	OpenAI Computer Use Agent
`anthropic-cua`	Anthropic Computer Use Agent
`ui-tars`	UI-TARS model

Specify the engine when running a task:

from skyvern.schemas.runs import RunEngine

result = await skyvern.run_task(
    prompt="Extract pricing data",
    url="https://example.com",
    engine=RunEngine.skyvern_v2
)

Quick Reference

I want to…	Use
Run a one-off automation	Task
Build a reusable multi-step process	Workflow
Keep a browser open between tasks	Browser Session
Skip login on repeated runs	Browser Profile
Store secrets securely	Credentials
Debug a failed run	Artifacts

Next Steps

API Quickstart

Run your first task in 5 minutes

Build Workflows

Create multi-step automations

Workflow Blocks

Full reference for all block types

API Reference

Complete API documentation

Getting Started

Running Automations

Multi-Step Automations

Optimization

Going to Production

Debugging

Self-Hosted Deployment

Tasks

Workflows

Blocks

Navigation & Interaction

Data & Files

Logic & Control Flow

Communication & Integration

Runs

Credentials

Browser Sessions & Profiles

Browser Sessions

Browser Profiles

Artifacts

Engines

Quick Reference

Next Steps

API Quickstart

Build Workflows

Workflow Blocks

API Reference

Getting Started

Running Automations

Multi-Step Automations

Optimization

Going to Production

Debugging

Self-Hosted Deployment

​Tasks

​Workflows

​Blocks

​Navigation & Interaction

​Data & Files

​Logic & Control Flow

​Communication & Integration

​Runs

​Credentials

​Browser Sessions & Profiles

​Browser Sessions

​Browser Profiles

​Artifacts

​Engines

​Quick Reference

​Next Steps

API Quickstart

Build Workflows

Workflow Blocks

API Reference

Tasks

Workflows

Blocks

Navigation & Interaction

Data & Files

Logic & Control Flow

Communication & Integration

Runs

Credentials

Browser Sessions & Profiles

Browser Sessions

Browser Profiles

Artifacts

Engines

Quick Reference

Next Steps