> For the complete documentation index, see [llms.txt](https://docs.allthingsghl.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.allthingsghl.com/ai-prompts/highlevel/ghl-voice-ai-prompts/call-management/call-recovery-features.md).

# Call Recovery Features

Objective

This guide provides ready-to-use, word-for-word prompts for GHL Voice AI to implement call recovery strategies, ensuring that: \
✅ AI follows up after dropped or disconnected calls via SMS \
✅ AI detects and responds to silence instead of hanging up abruptly \
✅ AI smoothly re-engages users after reconnection \
✅ AI maximizes the chances of completing the conversation and avoiding lost leads

1\. Understanding the Problem: Why Call Recovery Matters

🔹 Common Issues Without Call Recovery: Call drops or user hangs up → AI fails to follow up, leading to lost sales. User remains silent due to distractions or poor connection → AI hangs up instead of re-engaging. User disconnects unintentionally → No way to resume the conversation later. \
🔹 Solution: \
✅ Implement automated follow-up SMS when a call is dropped. \
✅ Use silence detection prompts to prevent AI from disconnecting too soon. \
✅ Ensure AI re-engages smoothly if the user reconnects.

2\. Step-by-Step AI Prompt Implementation for Call Recovery 🔹 Step 1: Detecting Silence & Attempting to Re-Engage

✅ Objective: AI must detect silence and check if the user is still present before disconnecting. 📌 Copy-and-Paste Prompt (Silence Detection): 🔹 "I just want to make sure I didn’t lose you. Are you still there?" 🔹 "Hello? I want to make sure we stay connected. Can you hear me?" 🔹 "It seems like there’s a pause. If you’re still there, just say anything and we’ll continue." ✔ Real-Life Example: Before (Bad AI Response - No Silence Detection): 🔹 User: (Gets distracted and remains silent for 10 seconds.) 🔹 AI: (Automatically hangs up.) ❌ After (Optimized AI Response with Silence

Detection): 🔹 User: (Gets distracted and remains silent for 10 seconds.) 🔹 AI: "I just want to make sure I didn’t lose you. Are you still there?" ✅ 📌 Where to Use in GHL: Place this before AI hangs up due to inactivity (after 7-10 seconds of silence).

🔹 Step 2: Handling Silence If the User Does Not Respond

✅ Objective: If the user does not respond after the initial silence check, AI must provide a soft exit and set up a recovery option. 📌 Copy-and-Paste Prompt (Graceful Call Exit Due to Silence): 🔹 "It looks like we got disconnected. If you’re still there, just say something, and we can continue." 🔹 "I may have lost you, but no worries! I’ll send you a text with next steps just in case." 🔹 "It seems like we’ve lost connection. I’ll follow up via text so you don’t miss anything." ✔ Real-Life Example: Before (Bad AI Response - Abrupt Hang-Up): 🔹 User: (Silent for 15 seconds) 🔹 AI: (Instantly disconnects.) ❌ After (Optimized AI Response with Graceful Exit): 🔹 User: (Silent for 15 seconds) 🔹 AI: "I may have lost you, but no worries! I’ll send you a text with next steps just in case." ✅ 📌 Where to Use in GHL: Place this before AI hangs up due to extended silence (15+ seconds).

🔹 Step 3: Sending an Automated Follow-Up SMS After a Dropped Call

✅ Objective: If the user disconnects unexpectedly, AI must send a follow-up SMS to re-engage them. 📌 Copy-and-Paste Prompt (Follow-Up SMS for Dropped Calls): 🔹 "Looks like we got disconnected! If you’d like to continue, reply YES and I’ll call you back." 🔹 "Oops! It seems like the call dropped. Need to finish our chat? Just reply YES." 🔹 "Hey, I think we lost connection! Want me to call you back? Just say YES." ✔ Real-Life Example: Before (Bad AI Response - No Follow-Up): 🔹 User: (Accidentally disconnects.) 🔹 AI: (Does nothing—lead is lost forever.) ❌ After (Optimized AI Response with Follow-Up SMS): 🔹 User: (Accidentally disconnects.) 🔹 AI (SMS sent immediately): "Oops! It seems like the call dropped. Need to finish our chat? Just reply YES." ✅ 📌 Where to Use in GHL: Set up an SMS trigger that activates if the call disconnects unexpectedly.

🔹 Step 4: Resuming the Conversation When the User Responds to the SMS

✅ Objective: If the user replies YES to the follow-up SMS, AI must seamlessly pick up where it left off instead of restarting. 📌 Copy-and-Paste Prompt (Resuming a Call from Follow-Up SMS): 🔹 "Great! Let’s continue where we left off. You were asking about \[Last Topic]." 🔹 "Awesome! I’m glad we could reconnect. Last time, we were discussing \[Last Conversation Point]. Want to pick up from there?" 🔹 "Glad to have you back! We were just talking about \[Last Topic]. Let’s continue." ✔ Real-Life Example: User: (Replies “YES” to follow-up SMS.) AI (Call resumes): 🔹 "Awesome! I’m glad we could reconnect. Last time, we were discussing pricing. Want to pick up from there?"

✅ 📌 Where to Use in GHL: Set up a call-back trigger that resumes the last conversation instead of restarting from the beginning.

3\. Full Example of an Optimized AI Call Recovery Flow (With Silence Detection & Follow-Up SMS)

🚀 Scenario: AI Detects Silence & Re-Engages the User

🔹 AI: "Hi, this is Sarah from \[Company Name]. How can I assist you today?" 🔹 User: (Gets distracted and remains silent for 10 seconds.) 🔹 AI: "I just want to make sure I didn’t lose you. Are you still there?" 🔹 User: (Remains silent for another 10 seconds.) 🔹 AI: "I may have lost you, but no worries! I’ll send you a text with next steps just in case." 📌 Outcome: AI detects silence, attempts to re-engage, and sends a follow-up SMS instead of abruptly disconnecting.

🚀 Scenario: AI Handles a Dropped Call & Follows Up via SMS

🔹 User: (Call drops unexpectedly.) 🔹 AI: (Immediately triggers an SMS.) 🔹 SMS: "Oops! It seems like the call dropped. Need to finish our chat? Just reply YES." 🔹 User: (Replies YES.) 🔹 AI (resumes): "Great! Let’s continue where we left off. You were asking about our pricing options—let’s go over those now." 📌 Outcome: AI re- engages the user instead of losing them forever.

4\. Implementation Checklist for GHL Voice AI Agents

✅ Enable silence detection prompts → Prevent AI from hanging up too soon. \
✅ Use follow-up SMS triggers for dropped calls → Give users a way to reconnect. \
✅ Ensure AI resumes conversations instead of restarting → Saves user time & improves experience. \
✅ Test AI calls to identify where users typically drop off and adjust recovery strategies accordingly.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.allthingsghl.com/ai-prompts/highlevel/ghl-voice-ai-prompts/call-management/call-recovery-features.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.