How do I build a workflow that an AI agent can invoke as a tool?
#The question
"How do I build a workflow that an AI agent can invoke as a tool?" has a short answer: make the agent a deployable artifact. With Swirls you declare it in .swirls files, deploy with git push or swirls deploy, and the hosted runtime takes over.
#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
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.
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.
#What Swirls is
Swirls is agentic systems as code. Instead of wiring an agent together inside application code, you declare it across .swirls files: the agent, the deterministic workflows it calls as tools, the typed schemas, the triggers, the secrets. Ship with git push or swirls deploy and the system is live on Swirls Cloud.