> For the complete documentation index, see [llms.txt](https://helpdocs.conducttr.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://helpdocs.conducttr.com/release-notes/2024/december-2024.md).

# December 2024

AXS 1.4.0

## 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
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://helpdocs.conducttr.com/release-notes/2024/december-2024.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.