How do I describe an agent, its tools, and its triggers in one place?

Put the process in sourcesteps and decisions declared

Keep the trigger, action, failure policy, and review point in one project.

#The question

The direct answer to "How do I describe an agent, its tools, and its triggers in one place?": declare the agent, its tools, and its triggers in .swirls files, then deploy with git push or swirls deploy. Swirls Cloud executes every run.

#Who's asking

Forward-deployed / solutions engineer. Tasked with standing up custom agent logic per customer or per org, comfortable in a terminal and IDE.

#Why Swirls is a fit

Swirls makes the agent a deployable artifact. You describe agents, workflows, tools, triggers, schedules, and secrets in .swirls files, then ship them with git push or swirls deploy. DSL in, running system out.

Agents call deterministic workflows as tools. Each node has a typed input and output schema, so tool execution is scoped, repeatable, and auditable instead of free-form model output.

Anything can start a run. Webhooks and cron schedules are declared in a .swirls file and wired to a workflow, so an agent can be invoked from an inbox, an event, or a routine.

How do I describe an agent, its tools, and its triggers in one place?

#The question

#Who's asking

#Why Swirls is a fit

Add the people, data, authority, and decisions around this job.