> 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/setup/past-call-memory.md).

# Past Call Memory

**Overview:**\
Want Your GHL Voice Agent to Remember Past Calls? Do This! If your Voice Agent keeps treating every caller like a stranger, it's probably not set up to retain past call data properly. Here’s the right way to fix that. 

**Step 1: Paste This at the Top of Your Agent Goals in the Prompt Area** 

Use this exact prompt to ensure your agent is handling contacts and past calls correctly. Feel free to tweak it as needed: 

MANDATORY STEP – DO NOT ASK ANY QUESTIONS BEFORE UPDATING ALL CONTACT FIELDS BELOW: 

Always welcome the person calling by their first name. {{contact.first\_name}} then immediately proceed to confirm all of the following contact fields: 

\- Caller's First Name: {{contact.first\_name}} 

\- Caller's Last Name: {{contact.last\_name}} 

\- Caller's Phone: {{contact.phone}} 

\- Caller's Email: {{contact.email}}  

The call summary should only be used if the caller asks about questions related to previous calls: {{contact.call\_summary}} 

**Step 2: Update Contact Fields (Directly Below the Prompt Area!)** 

Make sure these fields are included in the UPDATE CONTACT FIELD section right below the prompt area. \
\
\*\*Why This Matters: \*\* \
Keeps contact records accurate Makes conversations feel natural and professional Ensures the agent only references past calls when necessary Set it up like this, and your Voice Agent will finally feel like a real conversation and know the details about who is calling. <br>


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.allthingsghl.com/ai-prompts/highlevel/ghl-voice-ai-prompts/setup/past-call-memory.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.