```
When the workflow runs, Cyberdesk automatically resolves these URLs to display the image
to the AI agent.
Supported formats: PNG, JPEG, GIF, WebP. Maximum size: 10MB.
# Async Extraction Patterns
Source: https://docs.cyberdesk.io/concepts/async-extraction-patterns
Understanding synchronous, batch-scoped, and run-scoped async extraction modes
## Overview
Cyberdesk provides flexible async extraction modes that let you optimize workflow performance based on when and how you need extracted data. Understanding these patterns is key to building fast, efficient workflows.
success, task\_failed, error, or cancelled.
* Outputs, history, and output attachments are always cleared.
* Prior input attachments are kept unless you provide file\_inputs (then they are replaced).
* If you provide sensitive\_input\_values, new secrets are created; otherwise sensitive aliases are cleared.
* When a session\_id is present and the session is busy, immediate assignment is skipped and the retried run queues.
* Avoid sending both machine\_id and pool\_ids on retry; if both are present, pool\_ids take precedence.
# Upload from raw bytes
with open('./image.png', 'rb') as f:
image_bytes = f.read()
response = await client.workflows.upload_prompt_image(
file_content=image_bytes,
filename='my-image.png',
content_type='image/png'
)
# List all prompt images
response = await client.workflows.list_prompt_images()
for img in response.data:
print(f"{img.filename}: {img.supabase_url}")
# Get a fresh signed URL for an existing image
response = await client.workflows.get_prompt_image_signed_url(
path='org_xxx/prompt-assets/my-image.png'
)
print(f"Signed URL: {response.data.signed_url}")
print(f"Expires in: {response.data.expires_in} seconds")
# Delete an image
response = await client.workflows.delete_prompt_image(
path='org_xxx/prompt-assets/my-image.png'
)
```
Click on the button shown in this screenshot:
Then proceed to fill out the form.
``` Cyberdesk automatically resolves these URLs when running workflows, displaying the images to the AI agent.success, task\_failed, error, or cancelled.
* Outputs, history, and output attachments are always cleared.
* Prior input attachments are kept unless you provide file\_inputs (then they are replaced).
* If you provide sensitive\_input\_values, new secrets are created; otherwise sensitive aliases are cleared.
* When a session\_id is present and the session is busy, immediate assignment is skipped and the retried run queues.
* When machine\_id is provided, pool\_ids are ignored.
}
}
// List all prompt images
const { data: images } = await listWorkflowPromptImagesV1WorkflowsPromptImagesGet({
client: client._client
});
for (const img of images || []) {
console.log(`${img.filename}: ${img.supabase_url}`);
}
// Get a fresh signed URL for an existing image
const { data: signedData } = await getWorkflowPromptImageSignedUrlV1WorkflowsPromptImageSignedUrlGet({
client: client._client,
query: { path: 'org_xxx/prompt-assets/my-image.png' }
});
if (signedData) {
console.log(`Signed URL: ${signedData.signed_url}`);
console.log(`Expires in: ${signedData.expires_in} seconds`);
}
// Delete an image
await deleteWorkflowPromptImageV1WorkflowsPromptImageDelete({
client: client._client,
query: { path: 'org_xxx/prompt-assets/my-image.png' }
});
```
Click on the button shown in this screenshot:
Then proceed to fill out the form.
``` Cyberdesk automatically resolves these URLs when running workflows, displaying the images to the AI agent.⚡ Non-blocking (async) | 🐌 5-10 sec | ⚡ Instant | | **Decision Making** | ❌ Read-only | ✅ Dynamic decisions | ❌ Read-only | | **Runtime Variables** | ✅ Yes, when the prompt explicitly says to save/store them | ✅ Yes | ✅ Yes | | **Async Options** | ✅ Batch & Run scopes | ❌ Always synchronous | ❌ Always synchronous | | **Use Case** | Large-scale extraction, non-copyable content | Dynamic navigation, decisions | Fast field extraction | | **Cost** | 💳 Vision tokens | 💳 Vision tokens | 💰 No AI cost | ### When to Use Each **Use Extract Prompt When:** * Extracting large amounts of data for output * Working with non-copyable content (images, PDFs, charts) * Need parallel/async processing for speed * Extraction doesn't affect navigation decisions * Want to store runtime values while also returning an extraction result **Use [Focused Action](/workflow-prompting/focused-action) When:** * Making dynamic decisions during workflow * Conditional logic based on screen content * Selecting from lists based on runtime criteria * Verification steps that determine next actions **Use [Copy to Clipboard](/workflow-prompting/copy-to-clipboard) When:** * Text is selectable and copyable * Need deterministic, byte-exact extraction * Speed is critical * Working with simple text fields (IDs, numbers, dates) ## Advanced Patterns ### Hybrid Extraction Strategy Combine all three methods for optimal performance: ```text theme={null} "Extract order data using the most efficient method for each field: Fast clipboard extraction (copyable fields): - Triple-click Order ID field, use copy_to_clipboard with key name 'order_id' - Triple-click Customer Name field, use copy_to_clipboard with key name 'customer_name' Vision-based extraction (non-copyable content): - Take screenshot of order items table with extract_prompt='Extract all line items as JSON array: {item_name, sku, quantity, unit_price, total}' and process_async='batch' - Take screenshot of shipping label image with extract_prompt='Extract tracking number and carrier name' and process_async='batch' Dynamic decision (navigation): - Use focused_action to check if order requires special handling based on total amount All values automatically included in final output." ``` ### Cascading Extractions Extract summary data first, then detailed data based on results: ```text theme={null} "Step 1 - Summary (Synchronous): Take screenshot with extract_prompt='Count how many pending orders are visible and return as: {pending_count: number}' Step 2 - Details (Batch-Scoped): If pending_count > 0, for each pending order: - Take screenshot with extract_prompt='Extract order details as JSON' and process_async='batch' - Click next order - Repeat Step 3 - Analytics (Run-Scoped): Take screenshot of analytics dashboard with extract_prompt='Extract complete analytics: sales trends, top products, customer segments' and process_async='run' Continue workflow while analytics extraction runs in background." ``` ### Progressive Detail Extraction Start with high-level extraction, add detail as needed: ```text theme={null} "Navigate to dashboard. Level 1 - Overview (Run-Scoped): Take screenshot with extract_prompt='Extract high-level metrics: total_revenue, total_orders, active_customers, growth_rate. Store total_revenue as runtime variable.' and process_async='run' Level 2 - Category Breakdown (Batch-Scoped): For each product category: - Take screenshot with extract_prompt='Extract category sales data as JSON' and process_async='batch' - Click next category Level 3 - Individual Products (Decision-Based): Use focused_action to identify top 5 products by revenue, then for each: - Take screenshot with extract_prompt='Extract detailed product metrics' and process_async='batch' All extractions complete before final output generation." ``` ### Runtime Variable Integration Use run-scoped extraction to set variables for later workflow steps: ```text theme={null} "Open invoice {invoice_number}. Take screenshot with extract_prompt='Extract invoice_date, due_date, and total_amount as runtime variables. Then extract complete line item details, tax breakdown, and payment terms.' and process_async='run' While that extraction runs in background: - Navigate to customer portal - Login with credentials - Go to payment page - Wait for {{total_amount}} to be available - Enter {{total_amount}} in payment field - Set payment date to {{due_date}} - Submit payment The full invoice details will be in the final output along with payment confirmation." ``` ## Model Override (Optional) You can optionally specify which model to use for extraction by adding the `model` parameter: ```text theme={null} Take screenshot with extract_prompt="Extract all invoice data as JSON" and model="Sonnet 4.5" ``` Unlike `focused_action`, any vision-capable model works for `extract_prompt`—it doesn't need computer use capabilities since it only reads the screen without performing actions.