Example code snippets (#454)

* feat: add phone support agent workflow example

* feat: update navigation to link new customer support hotline example

* feat: add screenshots for customer support hotline example

* fix: customer support hotline intro paragraph

* fix(customer-support-hotline): image URLs

* fix(customer-support-hotline): remove broken link from outro

* chore (customer-support-hotline): refine copy, add videos

* chore(customer-support-hotline): delete unnecessary screenshots

* fix(customer-support-hotline): slug

* feat(appointment-scheduling): initial commit

* feat(banking-customer-support): update example to cover a banking use case

* chore(inbound-support): address review feedback, fix system prompt

* feat(appointment-scheduling): new workflow example

* feat(clinic-triage-scheduling): new workflow example

* feat(ecommerce-order-management): new workflow example

* feat(outbound-sales): new workflow example

* chore: delete pizza example

* fix: broken video URLs

* chore: update navigation to include new workflow examples

* fix(inbound-support): broken video URL

* chore: update `overview.mdx` to display new examples

* feat(call-forwarding): update doc to incentivize use of dashboard

* feat(using-query-tool): update doc to incentivize use of dashboard

* feat(custom-tools): update doc to incentivize use of dashboard

* feat(workflows/overview): add doc

* feat(workflows/quickstart): add doc

* feat(workflows): move docs, add new videos

* chore: update nav to include workflow docs

* feat(docs-agent): add code snippets

* feat(examples/inbound-support): add code snippets

* feat(examples/outbound-call-python): add code snippets

* feat(examples/voice-widget): add code snippets

* feat(quickstart/dashboard): add code snippets

* feat(workflows/quickstart): add code snippets

* feat(workflows/appointment-scheduling): add code snippets

* feat(workflows/clinic-triage-scheduling): add code snippets

* feat(workflows/ecommerce-order-management): add code snippets

* feat(workflows/outbound-sales): add code snippets

* chore: delete `.DS_Store`

* feat(workflows/quickstart): new code examples

* feat(examples/docs-agent): new code examples

* feat(examples/inbound-support): new code examples

* feat(examples/voice-widget): new code examples

* feat(quickstart/dashboard): new code examples

* feat(quickstart/phone): new code examples

* feat(workflows/outbound-sales): new code examples

* feat(workflows/ecommerce-order-management): new code examples

* feat(workflows/appointment-scheduling): new code examples

* feat(workflows/clinic-triage-scheduling): new code examples

* chore: add other pm install options, cleanup

* chore: replace `gpt-4` occurrences with `gpt-4o` to stay up-to-date

* chore: replace `gpt-3.5-turbo` occurrences with `gpt-4o` to stay up-to-date

* chore: delete `outbound-call-python` example

* fix: code examples

* fix: delete duplicate merge doc

* chore: cleanup video assets

* chore: cleanup merge duplicates, restructure dirs for consistency

Author: goosewin

fern/assistants/personalization.mdx

@@ -105,7 +105,7 @@ This approach is ideal for use cases like customer support, account management,
             name: "Dynamic Customer Support Assistant",
             model: {
               provider: "openai",
-              model: "gpt-4",
+              model: "gpt-4o",
               messages: [{
                 role: "system",
                 content: `You are helping ${customer.name}, a ${customer.tier} member since ${customer.createdAt}.`

fern/customization/custom-llm/tool-calling-integration.mdx

@@ -241,7 +241,7 @@ Once your endpoints are set up, try testing them with these cURL commands.
 curl -X POST https://custom-llm-url/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
-        "model": "gpt-3.5-turbo",
+        "model": "gpt-4o",
         "messages": [
           {"role": "user", "content": "I need a payment link."}
         ],
@@ -268,7 +268,7 @@ Streaming chunks eventually include the result (e.g., a payment link) returned b
 curl -X POST https://custom-llm-url/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
-        "model": "gpt-3.5-turbo",
+        "model": "gpt-4o",
         "messages": [
           {"role": "user", "content": "Please transfer my call."}
         ],
@@ -423,4 +423,4 @@ By building each layer step by step and testing with cURL, you can fine-tune you
 For your convenience, you can find the complete source code for this Custom LLM integration here:
 
 **[Custom LLM with Vapi Integration – Complete Code](https://codesandbox.io/p/devbox/gfwztp)**
-```
+```

fern/customization/custom-transcriber.mdx

@@ -63,8 +63,26 @@ You'll learn how to:
     mkdir vapi-custom-transcriber
     cd vapi-custom-transcriber
     npm init -y
+    ```
+    
+    <CodeBlocks>
+    ```bash title="npm"
     npm install ws express dotenv @deepgram/sdk
     ```
+
+    ```bash title="yarn"
+    yarn add ws express dotenv @deepgram/sdk
+    ```
+
+    ```bash title="pnpm"
+    pnpm add ws express dotenv @deepgram/sdk
+    ```
+
+    ```bash title="bun"
+    bun add ws express dotenv @deepgram/sdk
+    ```
+    </CodeBlocks>
+    
     Create a `.env` file with the following content:
     ```env
     DEEPGRAM_API_KEY=your_deepgram_api_key

fern/customization/jwt-authentication.mdx

@@ -31,7 +31,7 @@ For example, it can be used to restrict which API endpoints the token can access
 
 <Note>
   As of writing, the only publicly scoped API endpoint is
-  https://api.vapi.ai//call/web, which is used for Web Call creation. All other
+  https://api.vapi.ai/call/web, which is used for Web Call creation. All other
   endpoints are privately scoped.
 </Note>
 
@@ -136,18 +136,7 @@ If you set the scope to `public`, you can use it to make authenticated API reque
 ```
 import Vapi from '@vapi-ai/web';
 
-const vapi = new Vapi({
-  token: 'your-jwt-token',
-});
+const vapi = new Vapi('your-jwt-token');
 
 vapi.start('your-assistant-id');
 ```
-
-## Notes
-
-- With the generated token, you can authenticate API requests to any endpoint requiring authentication. The token will be valid for the duration specified in the options (1 hour in this case).
-- If you don't specify `token` in the JWT payload, the token will be public.
-
-## Conclusion
-
-This documentation covered the basics of generating a JWT token and demonstrated how to use the token to make authenticated API requests. Ensure that your environment variables (e.g., `ORG_ID` and `PRIVATE_KEY`) are correctly set up before running the code.

fern/docs.yml

@@ -746,15 +746,13 @@ redirects:
   - source: "/multilingual/introduction"
     destination: "/multilingual"
   - source: "/outbound_sales"
-    destination: "/examples/outbound-sales"
+    destination: "/examples/lead-qualification"
   - source: "/technical_support"
     destination: "/examples/inbound-support"
   - source: "/pizza_website"
     destination: "/examples/inbound-support"
   - source: "/examples/pizza-website"
     destination: "/examples/inbound-support"
-  - source: "/outbound_call_python"
-    destination: "/examples/outbound-call-python"
   - source: "/voice_widget"
     destination: "/examples/voice-widget"
   - source: "/clients"