diff --git a/docs/advanced/chat_functions/local.md b/docs/advanced/chat_functions/local.md
index c10f7c981..fe8963c67 100644
--- a/docs/advanced/chat_functions/local.md
+++ b/docs/advanced/chat_functions/local.md
@@ -4,10 +4,10 @@ All request payloads below follow the [μEd API](https://mued.org/) `ChatRequest
 
 ## Run Unit Tests
 
-You can run the unit tests using `pytest`:
+You can run the unit tests using `pytest`. Run it from the repository root with `PYTHONPATH=.` set (as CI does), so that the `tests` and `src` packages resolve correctly:
 
 ```bash
-pytest
+PYTHONPATH=. pytest
 ```
 
 ## Run the Chat Script
@@ -46,12 +46,20 @@ docker run -e OPENAI_API_KEY={your key} -e OPENAI_MODEL={your LLM chosen model n
 docker run --env-file .env -it --name my-lambda-container -p 8080:8080 llm_chat
 ```
 
-This will start the chat function and expose it on port `8080` and it will be open to be curl:
+This will start the chat function and expose the chat API on port `8080`, ready to be curled:
 
 ```bash
-curl --location 'http://localhost:8080/2015-03-31/functions/function/invocations' \
+curl --location 'http://localhost:8080/chat' \
 --header 'Content-Type: application/json' \
---data '{"body":"{\"messages\": [{\"role\": \"USER\", \"content\": \"hi\"}]}"}'
+--header 'X-Api-Version: 0.1.0' \
+--data '{"messages": [{"role": "USER", "content": "hi"}]}'
+```
+
+Health check:
+
+```bash
+curl --location 'http://localhost:8080/chat/health' \
+--header 'X-Api-Version: 0.1.0'
 ```
 
 ### Call Docker Container
@@ -69,9 +77,11 @@ python tests/manual_agent_requests.py
 POST URL:
 
 ```bash
-http://localhost:8080/2015-03-31/functions/function/invocations
+http://localhost:8080/chat
 ```
 
+Requests may include an `X-Api-Version: 0.1.0` header.
+
 Minimal body — only the required `messages` field:
 
 ```JSON
diff --git a/docs/advanced/chat_functions/quickstart.md b/docs/advanced/chat_functions/quickstart.md
index 1de3111c7..f9986cb61 100644
--- a/docs/advanced/chat_functions/quickstart.md
+++ b/docs/advanced/chat_functions/quickstart.md
@@ -22,7 +22,7 @@ Per the μEd `ChatRequest` schema, **only `messages` is required** — `conversa
 	- For new functions: use the template repo [chat-function-boilerplate](https://github.com/lambda-feedback/chat-function-boilerplate) via *Use this template > Create a new repository*, choosing the `Lambda Feedback` organisation as the owner. **Make sure the new repository is set to public (it needs access to organisation secrets and GitHub deployment protection rules)**.
 	- For existing functions: please make your changes on a new separate branch
 
-2. Add your LLM credentials to a `.env` file in the root of the repository. OpenAI, Google AI and Ollama are supported out of the box:
+2. Add your LLM credentials to a `.env` file in the root of the repository. OpenAI, Google AI, OpenRouter, Azure OpenAI and Ollama are supported out of the box:
 
 	```bash
 	# If you use OpenAI:
@@ -33,6 +33,11 @@ Per the μEd `ChatRequest` schema, **only `messages` is required** — `conversa
 	GOOGLE_AI_API_KEY
 	GOOGLE_AI_MODEL
 
+	# If you use OpenRouter:
+	OPENROUTER_API_KEY
+	OPENROUTER_MODEL
+	OPENROUTER_BASE_URL
+
 	# If you use Ollama:
 	OLLAMA_MODEL
 	OLLAMA_BASE_URL
@@ -54,9 +59,11 @@ Per the μEd `ChatRequest` schema, **only `messages` is required** — `conversa
 
 	4. **`src/agent/context.py`**: converts the μEd API `context` and `user` dictionaries into the prompt text given to the LLM.
 
-	5. Update the `config.json` file with the name of the chat function.
+	5. **`index.py`**: the entrypoint of the deployed function. It registers the `chat` and `chat health` handlers from `src/module.py` with `lf_toolkit`'s server.
+
+	6. Update the `config.json` file with the name of the chat function.
 
-	6. Please add a `README.md` file (and update `docs/`) to describe the use and behaviour of your chatbot.
+	7. Please add a `README.md` file (and update `docs/`) to describe the use and behaviour of your chatbot.
 
 ## Request and response schema
 
@@ -154,10 +161,10 @@ Expected response:
 
 ## Testing your changes
 
-Changes can be tested locally by running the pipeline tests using:
+Changes can be tested locally by running the pipeline tests from the repository root with `PYTHONPATH=.` set (as CI does):
 
 ```bash
-pytest
+PYTHONPATH=. pytest
 ```
 
 [Running and Testing Chat Functions Locally](local.md){ .md-button }