diff --git a/examples/folio/sanderling/spec-llm.ts b/examples/folio/sanderling/spec-llm.ts
new file mode 100644
index 0000000..e5f33de
--- /dev/null
+++ b/examples/folio/sanderling/spec-llm.ts
@@ -0,0 +1,18 @@
+// LLM action-backend variant of spec.ts.
+//
+// The properties and the login `setup` are reused verbatim; only the action
+// generator changes. Instead of the seeded fuzzer drawing a random candidate,
+// `llm({ model })` hands selection to an OpenRouter vision model: each step it
+// sees the screenshot plus the candidate list the system already enumerates and
+// returns which candidate to act on. The candidate set, the typed input values,
+// action execution, and the trace are all identical to the seeded run.
+//
+// Requirements:
+//   - OPENROUTER_API_KEY in the environment.
+//   - A model that supports image input AND strict json_schema structured
+//     outputs (e.g. "openai/gpt-4o"). A model lacking either fails clearly.
+import { llm } from "@sanderling/spec";
+
+export { properties, setup } from "./spec";
+
+export const actionsRoot = llm({ model: "openai/gpt-4o" });