How do I stop my AI agent from doing unpredictable things?
#The question
When someone asks "How do I stop my AI agent from doing unpredictable things?", they want a repeatable path from definition to running system. Swirls gives you one: .swirls files describe the system, and git push or swirls deploy ships it to Swirls Cloud.
#Who's asking
Security / compliance owner. Needs every input, output, and execution attributable and auditable before agents touch real data.
#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.
You control the inputs and outputs of every node. The reasoning layer is small and explicit, and the execution around it is deterministic and inspectable.
Every user and machine execution is uniquely identified, and every node type supports a human-in-the-loop checkpoint. Workflows are declarative, repeatable, and auditable by construction.
#What Swirls is
Swirls is agentic systems as code. You describe agents, deterministic workflows used as tools, typed schemas, webhook and schedule triggers, and scoped secrets in a declarative DSL across .swirls files. Deploy with git push or swirls deploy and Swirls Cloud runs the system. DSL in, running system out.