# December 2024

## December 23rd, 2024

### New Features

#### LISA Session Persistence <a href="#id-1.-lisa-v2" id="id-1.-lisa-v2"></a>

The new **Session Persistence** feature allows users to save and retrieve their session history effortlessly, ensuring continuity and improving workflow efficiency.

**Who Benefits?**

This feature is ideal for designers who engage in multi-session tasks, such as project planning, extended discussions, or ongoing learning. By reducing repetitive setup, it offers a smoother and more seamless user experience.

**Feature Highlights**

* **Session Persistence and Retrieval**: LISA now saves messages automatically, allowing you to resume conversations without starting over.
* **Seamless Continuation**: Reopen sessions exactly where you left off, ensuring uninterrupted workflows and interactions.
* **Optimized Session Usage**: Tokens are consumed only for new sessions, making resource usage more efficient.
* **Session Visibility**: Easily view your sessions by categories such as "Today," "Last Week," "Previous Weeks". Also view how many days are left before the session expires.&#x20;

#### **Additional Notes** <a href="#id-1.1.3-additional-notes" id="id-1.1.3-additional-notes"></a>

* Sessions remain active for **30 days** from their creation date.
* **Deleted sessions** are permanently removed from your session history and cannot be restored.

### **Improvements**

#### Improvements on AXS Canvas <a href="#id-1.2.1-improvements-on-axs-canvas" id="id-1.2.1-improvements-on-axs-canvas"></a>

Updates on AXS Canvas prompts to keep them up to date with the latest AI models.

### Channel Refactoring

This update includes the **Checklist and Social Watch** channels, improving overall performance, scalability, and reliability across functionalities.


---

# Agent Instructions: 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:

```
GET https://helpdocs.conducttr.com/release-notes/2024/december-2024.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.