---
title: "Auto model mode | Langdock Changelog"
description: "Auto is our new model routing option that automatically selects a suitable model for your task. Instead of manually choosing between different models for…"
url: "https://langdock.com/changelog/auto-mode"
language: "en"
---

[Changelog](https://langdock.com/changelog)

May 6, 2026

# Auto model mode

Auto is our new model routing option that automatically selects a suitable model for your task.

Instead of manually choosing between different models for every prompt, Auto analyzes the first message of a conversation to understand the request and estimate its complexity. Based on that initial assessment, it selects a model for the rest of the conversation.

The goal is not to replace manual model selection entirely. You can still switch to other models at any point in a conversation. Auto is designed primarily for everyday work: quick questions, drafting, summarizing, rewriting, analysis, and other common tasks where you should not have to think about which model is suitable.

By taking away this small but frequent model-choice decision, Auto helps you work faster and make better use of your usage limits by avoiding costly models for simpler tasks. We will continue to improve the routing logic over time, expand the available model choices, and use feedback from users to make the experience more accurate and flexible.

#### Usage transparency in the model selector

We've added a usage bar directly in the model selector, so you can see at a glance how much usage roughly each model consumes. This makes it easier to understand your limits, make informed model choices, and get the most out of Langdock.

Improvements

- **Simplified Reasoning Model Toggle**: Reasoning models now have a simple on/off toggle, replacing the previous approach of separate model entries. Switching between standard and reasoning mode is now cleaner and more intuitive.
- **Templates in Agents**: You can now attach and use document templates directly inside agents, making it easier to standardize outputs and give agents a consistent starting point for document generation.
- **Improved File Handling**: We've made significant improvements to how Langdock reads and processes files. Documents are now handled more reliably and accurately across a wider range of file types and sizes.
- **More robust template uploads**: Template uploads are now more resilient: edge cases that previously caused failures have been addressed, making the experience smoother and more dependable.
- **Agent feedback nudge**: Users will now receive a nudge to leave feedback for the agent they are using, helping agent owners iterate and improve their agents over time.
- **React icons support in presentation generation**: Our PPTX generation now supports React Icons, unlocking a much wider range of icons for use in AI-generated slides.
- **Filter agent feedback by version**: You can now filter agent feedback by the version it was submitted against. This makes it much easier to track how changes to your agent affect user satisfaction over time.

[OlderGPT-5.5](https://langdock.com/changelog/gpt-55) [NewerNew Document Editor](https://langdock.com/changelog/new-document-editor)
