Hey, I got this automation working in this video but for some reason vapi doesn't get any of my data back (says "hello first name"). I copied everything exact from his video. There's no errors or anything so I have no clue what's going on. Does anyone know whats happening? https://cdn.discordapp.com/attachments/1256394401689632829/1256394546074353766/image.png?ex=66809c1a&is=667f4a9a&hm=6cd84c6bf4da9e5856dfba82ac56c8e4dc0630a8b8b56ad6d0bd902e87c83edf&

@unpaired Hello! I'm glad to hear you've been working on an automation with VAPI. It sounds like there might be an issue with the data binding or variable passing in your setup, especially if the system is returning a generic "hello first name" without the actual name. To help you better, I would need to know a bit more about how you're passing the data to VAPI. Are you using a specific platform or code to integrate VAPI? If you could provide details on the method you're using to send data to VAPI, I can give you more targeted advice. In the meantime, here are a few general things you can check: 1. **Variable Names**: Ensure that the variable names in your code exactly match those expected by VAPI. Even a small typo can cause the data not to be passed correctly. 2. **Data Flow**: Trace the data flow from the source to VAPI to make sure that the data is being captured and sent as expected. 3. **API Call**: If you're making an API call, double-check the payload to ensure the data is included and correctly formatted. 4. **Logs/Debugging**: If possible, use any logging or debugging tools available to you to see what data is being received by VAPI. If you're still having trouble, please provide more details or consider reaching out to our support team for a more in-depth look into your issue. Would you like me to send an email to our support team on your behalf?

im sending the data back via a webhook in this json format:

json
 {
   "assistant":{
      "name":"test",
      "model":{
         "model":"gpt-4o",
         "messages":[
            {
               "role":"system",
               "content":"Have a conversation about life.\n\n###User Details\n**First Name:** Jen\n**Last Name:** Moore\n**Email:** jannis@moore.test\n**Phone Number:** (redacted))"
            }
         ],
         "provider":"openai",
         "temperature":1
      },
      "voice":{
         "voiceId":"andrew",
         "provider":"azure"
      },
      "serverUrl":"(redacted)",
      "transcriber":{
         "model":"nova-2",
         "language":"en",
         "provider":"deepgram"
      },
      "firstMessage":"Hello Jen, this is Ava. How may I assist you today?",
      "hipaaEnabled":null,
      "clientMessages":[
         "transcript",
         "hang",
         "function-call",
         "speech-update",
         "metadata",
         "conversation-update",
         "function-call-result",
         "model-output",
         "status-update"
      ],
      "endCallMessage":null,
      "endCallPhrases":null,
      "serverMessages":[
         "end-of-call-report",
         "status-update",
         "hang",
         "function-call",
         "speech-update",
         "conversation-update",
         "model-output",
         "phone-call-control"
      ],
      "backgroundSound":null,
      "recordingEnabled":null,
      "voicemailMessage":null,
      "endCallFunctionEnabled":null,
      "dialKeypadFunctionEnabled":null
   }
}

and my original prompt is:

Have a conversation about life.

###User Details
**First Name:** [first_name]
**Last Name:** [last_name]
**Email:** [email]
**Phone Number:** [phone_number]

It is because of this "end-of-call-report", "status-update", "hang", "function-call", "speech-update", "conversation-update", "model-output", "phone-call-control" Just use the thing that you want.

Ill try that, thanks!

@Sahil i have the same issue; i removed unnecessary fields from "serverMessages" but it doesn't help; Make.com webhook responds with this JSON object :

json
{
  "assistant": {
    "name": "Agent",
    "model": {
      "model": "gpt-3.5-turbo",
      "toolIds": ["2ef190da-ec83-4f57-b427-1f88dc394df7"],
      "messages": [
        {
          "role": "system",
          "content": "You are an agent."
        }
      ],
      "provider": "openai",
      "maxTokens": 80
    },
    "voice": {"voiceId": "fr-FR-DeniseNeural", "provider": "azure"},
    "serverUrl": null,
    "transcriber": {
      "model"   : "nova-2"  ,
      "language": "fr"      ,
      "provider": "deepgram"
    },
    "firstMessage": "Hello Blurryface. How i can help you today?",
    "hipaaEnabled": null,
    "clientMessages": [
      "transcript"         , "hang"               , "function-call"      ,
      "speech-update"      , "metadata"           , "conversation-update"
    ],
    "endCallMessage": null,
    "endCallPhrases": null,
    "serverMessages": [
      "speech-update"      , "status-update"      ,
      "conversation-update"
    ],
    "backgroundSound": null,
    "recordingEnabled": null,
    "voicemailMessage": null,
    "endCallFunctionEnabled": null,
    "dialKeypadFunctionEnabled": null
  }
}

can you send me call_id? @0xBLURRYFΛCE

sure thing @Sahil

also this didnt fix my issue

This is quite strange.

im free anytime today, but yeah i just tried it again and its just not updating my prompt https://cdn.discordapp.com/attachments/1256394401689632829/1257444275600228533/image.png?ex=66846dbd&is=66831c3d&hm=fe6bacfa99dcdc58646c17a9a1dde4fe34a78caa59daa22b262df813d2bfc850&

I'm also free anytime today

same this worked for me, weird

you have to use a filter @unpaired

ah i see

and also remove all unnecessary fields from server messages

yeah

@Sahil it should be possible to remove all messages from "server messages" (maybe possible through the API, i didn't try)

im not sure who would use

speech-update

ngl because it used like 100 operations in a few seconds

yeah yeah i spent 5% of my Make.com quota because of this s*** 😄

You can do it just don't remove the tools-calling and function-calling. Apart from it, you can remove the rest of them