> For the complete documentation index, see [llms.txt](https://docs.maiagent.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.maiagent.ai/release-note/untitled/archives/11.md).

# November 2025

## v2025.11.2899 <a href="#v2025-11-2899" id="v2025-11-2899"></a>

***

### ✨ New Features

* **AI Assistant Settings Interface Optimization**: Optimized the AI assistant settings interface, enhancing visual presentation and adding configuration hints to help users configure models more clearly.
* **Automated Bot Evaluation Scheduling**: The system provides automated conversation quality evaluation, disabled by default to avoid unexpected costs. Administrators can enable the toggle to run evaluations automatically on a regular schedule and use historical reports to track performance trends and catch issues early.
* **On-Premises Version Performance Metric Tracking**: On-premises version evaluation records now include performance metric tracking, displaying time to first token and message generation time to help identify performance bottlenecks.
* **Knowledge Base Tag Search Filtering**: A tag search feature has been added to the knowledge base settings page. When a knowledge base contains dozens of tag categories, you can quickly locate and edit specific tag content. Ideal for teams managing large knowledge systems.
* **Tool Usage Record Tracking**: When a bot calls external tools (e.g., querying an order system, sending notifications), the system records the complete execution process and results, making it easy to troubleshoot questions like "why didn't the bot successfully look up the customer's order."

### 🚀 Performance & Core Improvements

* **Real-Time Display of Knowledge Base Crawl Failure Reasons**: When a web crawl fails, the system directly displays the specific failure reason in the interface (e.g., site access denied, page not found, content format error), allowing administrators to troubleshoot issues themselves without contacting technical support.

### 😊 User Experience & UI Enhancements

* **Code Syntax Highlighting in Conversation Messages**: When a bot's reply contains code snippets, the system automatically detects the programming language and applies color highlighting, making technical support conversations clearer and easier to read. Ideal for customer service teams providing technical consultation.
* **Conversation Message Formatting Optimization**: Improved the display formatting of tables, lists, and quoted text in conversation messages, making structured content (e.g., price comparison tables, product specifications) clearer and easier to read.
* **Conversation Platform Timezone Default Fix**: Fixed the issue where the timezone setting was not correctly applied when creating a conversation platform, ensuring message timestamps display in the enterprise's local timezone.
* **New Instagram Channel Support**: Added Instagram channel integration, supporting receiving and managing Instagram messages through the conversation platform.


---

# 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.maiagent.ai/release-note/untitled/archives/11.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.