Is there a declarative way to build AI agents?
#The question
The direct answer to "Is there a declarative way to build AI agents?": 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.
Because the whole system is described in the Swirls DSL, you apply the same static analysis to agentic workflows that you already apply to code. The runtime enforces the policy you declared.
#What Swirls is
Swirls gives agents the workflow your code already has: files, reviews, versions, deploys. A declarative DSL describes agents, tools, triggers, schedules, and secrets across .swirls files. You validate locally, deploy with git push or swirls deploy, and Swirls Cloud runs the result.