How do I prove what an AI agent did after the fact?
#The question
If you are asking "How do I prove what an AI agent did after the fact?", you want the guarantee enforced by the runtime, not by convention. Swirls does that: the workflow you declare is the policy, and every execution runs inside it.
#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
The audit log is append-only and tamper evident. Every entry is linked to the one before it, so changing, deleting, or reordering history breaks the chain. You can export the log and verify it yourself.
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.
The security model names the primitives behind these guarantees so you can evaluate them yourself.
#What Swirls is
Swirls treats an agentic system the way Terraform treats infrastructure: declare it, review it, deploy it. .swirls files describe agents, deterministic workflows used as tools, typed schemas, triggers, and scoped secrets. git push or swirls deploy ships them to the hosted runtime.