Skip to main content
Install Webcompute, sign in, configure model access, run an agentic workflow against a real web application, and inspect the managed browser run.

​
Prerequisites

  • A Webcompute API key with the wc_key_ prefix.
  • A model profile or provider key for web agent.
  • A shell with curl.
API keys and provider keys are credentials. Do not paste real keys into prompts, source control, issue trackers, or shared transcripts.

​
Install Webcompute

​
Sign in

web login stores your Webcompute API key for CLI and MCP use. SDK code can also use WEBCOMPUTE_API_KEY.

​
Configure a model

Run the interactive setup:
The wizard saves a reusable model profile. If you accept the default profile name, the examples below use --profile browsing. You can also pass model access for one command:
Read model setup for profiles, routes, and provider environment variables.

​
Run your first web agent

This creates a managed browser, starts from SEC EDGAR, stays inside sec.gov, browses the public filing search, and returns a short result.
A successful run prints a final answer with filing metadata. The exact filing date and accession number depend on the live SEC site.
Expected shape:

​
What happened

The CLI agent path is a complete surface for standalone workflows and operator tasks. It uses the same managed browser runtime as the SDK, MCP, REST, and CDP surfaces. During the run, Webcompute can produce:
  • A final answer for humans.
  • JSON output when you use --json or --schema.
  • A browser ID and signed Debug UI URL while the CLI run is active when you opt into --debug-url.
  • Bounded observations and step summaries.
  • Status, events, recordings, files, downloads, and artifacts when the workflow creates them.
The CLI agent closes browsers it creates after the one-shot run. Use the SDK when the workflow needs to live inside an application, backend process, or recurring automation. Use choose your path after first success to decide whether this workflow should stay in the CLI, integrate with SDK web.agent(), run through MCP, or add advanced exact browser control.

​
Get machine-readable output

Use --json when another program will read the result:
Use --schema ./filings.schema.json when the run must return a validated JSON shape. The JSON envelope includes the run status, final text, structured output when requested, browser metadata when available, and redacted errors when the run fails. See results and evidence for the surface-by-surface shapes.

​
Inspect the run

Use --debug-url only when you intentionally want a signed live-browser link in the result:
Debug UI URLs are signed bearer capabilities. Share them only with people or systems that should control the live browser.
Webcompute Debug UI showing the active browser page, recording state, browser status, readiness, and timeline for a managed browser run The screenshot above shows the same inspection surface available for live agent runs: active page metadata, browser readiness, recording state, and timeline events. Recordings can preserve evidence after the browser closes. The Debug UI link is available only when the browser is still live. A one-shot web agent run closes browsers it creates after completion. Use SDK browser creation or SDK web.agent() with recording when your workflow needs longer inspection or durable replay evidence.

​
If the quickstart does not finish

​
Next steps

Choose your path

Decide whether to use CLI agent, SDK agent, MCP, REST, CDP, quick actions, or advanced exact control.

Review results and evidence

Learn what the CLI, SDK, MCP, REST, and quick actions return.

Run tasks with web agent

Learn model profiles, domain boundaries, schemas, secrets, approvals, and live inspection.

Try a richer task

Run an agentic workflow with fields, boundaries, JSON output, and blocker guidance.

Build with the SDK

Build agentic workflows into applications, backend services, and recurring automations.

Inspect and debug

Use live sessions, recordings, status, events, downloads, and errors when a run needs evidence.