Sandbox · Medium4 vCPU · 4 GiBParked
$ python report.py
✓ Loaded 3 exports
✓ Joined accounts and invoices
✓ Wrote report.pdf
CPU
Memory
Billed0:00by the second
report.pdfReady
Sandboxes
An isolated computer for every agent run
Run code, process files and call your systems, with the Adapt harness or your own. What a model writes never runs inside your app.
Use cases
What you can build with sandboxes.
Run untrusted code
Execute what a model writes in a machine that can’t touch your app.
Process large files
Load exports, transform them, return a report or a dataset.
Long-running jobs
Hand off work that takes minutes, and get the result when it’s done.
How it works
Prepare a report from several large exports.
The agent coordinates the task while the sandbox handles the data processing.
Load the files
Make the approved source files and tools available to the job.
Run the transformation
Execute code to normalize the inputs, join records and calculate the requested metrics.
Return the result
Save the report and return a summary with the output location, ready for someone to review.
import { Adapt } from '@adapt/sdk'
const box = await new Adapt()
.sandboxes.create({ size: 'medium' })
await box.files.upload('./q3-exports')
await box.run('python report.py')
await box.files.download('report.pdf')Pricing
What it costs to run.
Choose a size for each sandbox. Time is metered per second while it runs, and a parked sandbox costs nothing.
- $0.045per vCPU-hour, billed only while running
- $0.0175per GiB-hour of memory
| Size | vCPU | Memory |
|---|---|---|
| Small | 2 | 2 GiB |
| Small, more memory | 2 | 4 GiB |
| Medium | 4 | 4 GiB |
| Medium, more memory | 8 | 16 GiB |
| Large | 16 | 16 GiB |
| XLarge | 32 | 32 GiB |
Works with
Use it with the rest of Adapt.
The company agent combines all four with your tools, shared knowledge and the places your team already works.