Create AI agent by describing it
Turn a plain-English job into a cloud agent, review a real run, and freeze the accepted workflow for reuse.
Read the guide →From a job to a running workflow
AI agent use cases
Seven practical guides for creating, scheduling and embedding agents, generating media, using a saved browser and deploying your own model. Each recipe links its sources, shows an illustrative result and explains what you still need to configure.
Scheduled AI agents
Schedule a tested agent for a morning report, recurring research or structured output using cron and an explicit timezone.
Read the guide →AI agents for SaaS products
Embed a tested agent behind your SaaS backend, with customer-specific service connections and explicit builder billing.
Read the guide →Bulk image generation API
Plan a CSV-to-images workflow with a tested generation step, bounded concurrency and per-row execution records.
Read the guide →AI agent to monitor competitor prices
Build a daily change report for a bounded list of competitor pages, with source URLs and explicit comparison history.
Read the guide →Browser agents with saved logins
Use a connection-bound saved browser profile for recurring website work, while handling login expiry and human takeover explicitly.
Read the guide →Deploy your own model for an AI agent
Package a custom Python model, deploy its endpoint and verify the request contract before adding it to an agent workflow.
Read the guide →Start with one verified run
Connect only the services the job needs. Review one result and its cost, then freeze the accepted workflow before scheduling or embedding it. Missing product facts are marked explicitly inside each guide.
Sources checked 2026-10-23. Examples are documentation excerpts, not a claim that a paid run has been performed.