diff --git a/.github/workflows/deploy.yaml b/.github/workflows/deploy.yaml
new file mode 100644
index 0000000..1c58463
--- /dev/null
+++ b/.github/workflows/deploy.yaml
@@ -0,0 +1,17 @@
+name: Deploy Worker
+on:
+  push:
+  pull_request:
+  repository_dispatch:
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    timeout-minutes: 60
+    needs: test
+    steps:
+      - uses: actions/checkout@v2
+      - name: Build & Deploy Worker
+        uses: cloudflare/wrangler-action@v3
+        with:
+          apiToken: ${{ secrets.CF_API_TOKEN }}
+          accountId: ${{ secrets.CF_ACCOUNT_ID }}
diff --git a/README.md b/README.md
index c784629..eb551f3 100644
--- a/README.md
+++ b/README.md
@@ -2,15 +2,23 @@
 
 this project aims to convert / proxy Cloudflare Workers AI responses to OpenAI API compatible responses so Workers AI models can be used with any OpenAI / ChatGPT compatible client
 
+- supports streaming and non-streaming responses
+- rewrites the different models 'gpt-3' and 'gpt-4' to use `@cf/meta/llama-2-7b-chat-fp16`
+- if the openAI client can be configured to provide other model names, just put in the cloudflare model id instead of gpt-4
+
 ## installation
 
-tba
+[![Deploy to Cloudflare Workers](https://deploy.workers.cloudflare.com/button)](https://deploy.workers.cloudflare.com/?url=https://github.com/pew/cloudflare-workers-openai-mock)
 
-## features
+1. create a [Cloudflare Account](https://dash.cloudflare.com/)
+2. clone this repo
+3. run `npm run deploy`
 
-- supports streaming and non-streaming responses
-- rewrites the different models 'gpt-3' and 'gpt-4' to use `@cf/meta/llama-2-7b-chat-fp16`
-- if the openAI client can be configured to provide other model names, just put in the cloudflare model id instead of gpt-4
+after the script has been deployed, you'll get an URL which you can use as your OpenAI API endpoint for other applications, something like this:
+
+```
+https://openai-api.foobar.workers.dev
+```
 
 ## use with llm