> For the complete documentation index, see [llms.txt](https://docs.taskade.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.taskade.com/changelog/changelog-2026/february-2026/february-12-2026.md).

# February 12, 2026

## What's New:

### Upgrades to Agent Chat

We've upgraded our Agents to better match Taskade EVE's capabilities and interface. This update brings a cleaner UI, direct image uploads, and support for all LLM models already supported by EVE.

<figure><img src="/files/S2U41fOZzyqIfk0Lqnqa" alt="" width="563"><figcaption></figcaption></figure>

Public agents now have new customization options and the ability to make even more tool calls.

<figure><img src="/files/WjTLyrR02h3XFVVbpm9h" alt="" width="563"><figcaption></figcaption></figure>

***

## Improvements & Fixes:

* Improved the descriptions of some errors thrown in Automations.
* Improved LLM model hover descriptions
* Fixed an issue where the page would flicker or reload when first loading into Taskade.
* Fixed an issue where large Agent conversations in the project chat would cause the page to freeze.
* Fixed an issue where referral credits were not being credited properly.
* \[Hotfix] Restored the ability to export agent chats and fixed an issue where exported agent chats has missing timestamps.
* \[Hotfix] Restored the copy chat button, model information and timestamps for agent chat. These changes were also applied to the EVE chat.


---

# 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.taskade.com/changelog/changelog-2026/february-2026/february-12-2026.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.