diff --git a/README.md b/README.md
index 4c69cd1..6a8ba62 100644
--- a/README.md
+++ b/README.md
@@ -9,9 +9,14 @@ This repo helps quickly bootstrap an n8n demo environment using docker-compose.
 ### Setup
 - Clone this repo
 - **Optionally** edit the credentials in the `.env` file
-- If you have an Nvidia GPU, run `docker compose --profile gpu-nvidia up`
-- Otherwise to run inference services on your CPU, run `docker compose --profile cpu up`
-- Wait a couple of minutes for all the containers to become healthy.
+- Start the containers:
+    - If you have an Nvidia GPU, run `docker compose --profile gpu-nvidia up`
+    - Otherwise to run inference services on your CPU, run `docker compose --profile cpu up`
+- Wait a couple of minutes for all the containers to become healthy
+- Open http://localhost:5678 in your browser and fill in the details
+- Open the included workflow: http://localhost:5678/workflow/srOnR8PAY3u4RSwb
+- Wait until Ollama has downloaded the `llama3.1` model (you can check the
+  docker console)
 
 ### Included service endpoints
 - [n8n](http://localhost:5678/)
diff --git a/docker-compose.yml b/docker-compose.yml
index 07803e4..383d574 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -32,6 +32,17 @@ x-ollama: &service-ollama
   volumes:
     - ollama_storage:/root/.ollama
 
+x-init-ollama: &init-ollama
+  image: ollama/ollama:latest
+  networks: ['demo']
+  container_name: ollama-pull-llama
+  volumes:
+    - ollama_storage:/root/.ollama
+  entrypoint: /bin/sh
+  command:
+    - "-c"
+    - "sleep 3; OLLAMA_HOST=ollama:11434 ollama pull llama3.1"
+
 services:
   postgres:
     image: postgres:16-alpine
@@ -101,3 +112,15 @@ services:
             - driver: nvidia
               count: 1
               capabilities: [gpu]
+
+  ollama-pull-llama-cpu:
+    profiles: ["cpu"]
+    <<: *init-ollama
+    depends_on:
+      - ollama-cpu
+
+  ollama-pull-llama-gpu:
+    profiles: ["gpu-nvidia"]
+    <<: *init-ollama
+    depends_on:
+      - ollama-gpu
diff --git a/n8n/backup/workflows/srOnR8PAY3u4RSwb.json b/n8n/backup/workflows/srOnR8PAY3u4RSwb.json
index 26fc79d..5a8e5b3 100644
--- a/n8n/backup/workflows/srOnR8PAY3u4RSwb.json
+++ b/n8n/backup/workflows/srOnR8PAY3u4RSwb.json
@@ -30,6 +30,7 @@
     },
     {
       "parameters": {
+        "model": "llama3.1:latest",
         "options": {}
       },
       "id": "3dee878b-d748-4829-ac0a-cfd6705d31e5",