diff --git a/checkpoint.json b/checkpoint.json
new file mode 100644
index 000000000..2e61178b6
--- /dev/null
+++ b/checkpoint.json
@@ -0,0 +1,68 @@
+{
+  "timestamp": "2026-04-15T13:43:11.791580Z",
+  "current_node": "greet",
+  "completed_nodes": [
+    "start",
+    "greet"
+  ],
+  "node_retries": {},
+  "context_values": {
+    "internal.node_visit_count": 1,
+    "thread.start.current_node": "greet",
+    "failure_signature": "",
+    "internal.retry_count.greet": 0,
+    "internal.fidelity": "compact",
+    "internal.retry_count.start": 0,
+    "graph.goal": "Say hello and demonstrate a basic Fabro workflow",
+    "last_response": "Hello! I’m Fabro, and this is a test of the Fabro workflow engine.  \n\nI’m here to help demonstrate how a workflow can be started, executed, and observed end to end.",
+    "graph.rankdir": "LR",
+    "outcome": "success",
+    "internal.thread_id": "start",
+    "response.greet": "Hello! I’m Fabro, and this is a test of the Fabro workflow engine.  \n\nI’m here to help demonstrate how a workflow can be started, executed, and observed end to end.",
+    "current_node": "greet",
+    "last_stage": "greet",
+    "internal.run_id": "01KP8P2ZFA7TRZYG9J72J6FP4P",
+    "failure_class": ""
+  },
+  "node_outcomes": {
+    "start": {
+      "status": "success",
+      "usage": null
+    },
+    "greet": {
+      "status": "success",
+      "context_updates": {
+        "last_stage": "greet",
+        "response.greet": "Hello! I’m Fabro, and this is a test of the Fabro workflow engine.  \n\nI’m here to help demonstrate how a workflow can be started, executed, and observed end to end.",
+        "last_response": "Hello! I’m Fabro, and this is a test of the Fabro workflow engine.  \n\nI’m here to help demonstrate how a workflow can be started, executed, and observed end to end."
+      },
+      "notes": "Stage completed: greet",
+      "usage": {
+        "input": {
+          "usage": {
+            "model": {
+              "provider": "openai",
+              "model_id": "gpt-5.4-mini"
+            },
+            "tokens": {
+              "input_tokens": 4336,
+              "output_tokens": 47,
+              "reasoning_tokens": 29,
+              "cache_read_tokens": 0,
+              "cache_write_tokens": 0
+            }
+          },
+          "facts": {
+            "provider": "open_ai"
+          }
+        },
+        "total_usd_micros": 3594
+      }
+    }
+  },
+  "next_node_id": "exit",
+  "node_visits": {
+    "greet": 1,
+    "start": 1
+  }
+}
\ No newline at end of file
diff --git a/nodes/greet/prompt.md b/nodes/greet/prompt.md
new file mode 100644
index 000000000..190c70fa2
--- /dev/null
+++ b/nodes/greet/prompt.md
@@ -0,0 +1,4 @@
+Goal: Say hello and demonstrate a basic Fabro workflow
+
+
+Say hello! Introduce yourself and explain that this is a test of the Fabro workflow engine.
\ No newline at end of file
diff --git a/nodes/greet/provider_used.json b/nodes/greet/provider_used.json
new file mode 100644
index 000000000..c98e5e9c0
--- /dev/null
+++ b/nodes/greet/provider_used.json
@@ -0,0 +1,5 @@
+{
+  "mode": "agent",
+  "provider": "openai",
+  "model": "gpt-5.4-mini"
+}
\ No newline at end of file
diff --git a/nodes/greet/response.md b/nodes/greet/response.md
new file mode 100644
index 000000000..72a42c0fa
--- /dev/null
+++ b/nodes/greet/response.md
@@ -0,0 +1,3 @@
+Hello! I’m Fabro, and this is a test of the Fabro workflow engine.  
+
+I’m here to help demonstrate how a workflow can be started, executed, and observed end to end.
\ No newline at end of file
diff --git a/nodes/start/status.json b/nodes/start/status.json
new file mode 100644
index 000000000..ca3c7f851
--- /dev/null
+++ b/nodes/start/status.json
@@ -0,0 +1,6 @@
+{
+  "status": "success",
+  "notes": null,
+  "failure_reason": null,
+  "timestamp": "2026-04-15T13:43:09.490422Z"
+}
\ No newline at end of file