Changelog

We are excited to introduce project sharing, an update that has been requested frequently since we launched projects in July! 🚀

Until now, projects have been a great way to organize your own chats and configure context through instructions and files for smaller projects. With project sharing, we are turning them into a powerful collaboration tool. You can now share entire projects, including all contained chats, files, and instructions, with your colleagues or entire groups.

Why Project Sharing?

Projects have always been great for organizing your own work. But we noticed that many of you were using them to structure work that is actually done collaboratively. Collaboration often happens in context, not just in single messages. When working on projects like a marketing campaign, a research topic, or a coding sprint, you often need to share the full picture, including files, instructions, and history. Instead of sharing individual chats one by one, you can now give your team access to the entire context of a project and allow others to build on top of your work.

Key Features

Flexible Sharing
You can now share a project with specific users or groups in your workspace. Everyone with access can view the chats, files, and custom instructions within that project. This is perfect for onboarding new team members to a topic or keeping everyone aligned.

Better Organization
To help you manage shared and private projects, we have updated the project’s sidebar and added filtering options to the project view. You can now easily filter chats created “By you" or "By others" to keep your workspace clutter-free.

Granular Permissions
You stay in control of your data. When sharing a project, you can manage access by choosing the roles of your collaborators. Editors can share the project with others, change the project title, update instructions, and manage attached files. They can also add new conversations to the project. Users have read-only access. They can see project configurations, read all chats, and view project contents. All conversations added to a shared project, whether existing or new, are visible to all project members.

Important: Regardless of your role, you are the only one who can change, rename, or delete your own chats, even if the project is deleted.

Project Sharing is available starting today. To share a project, open your project and click on the "Share" button at the top right.

We can’t wait for your feedback and to hear how you collaborate! 🙌

We are bringing Langdock even closer to where many of you collaborate every day by adding Langdock to Microsoft Teams 🤝

With the new Microsoft Teams App, your team can now use Langdock models and Agents directly inside Teams - in a private chat or collaboratively in channels. This especially helps with small ad-hoc situations every day. Example use cases are translating text really quickly or researching smaller topics without needing to open Langdock.

How to use the Teams App

Private conversations with Langdock App
Chat 1:1 with Langdock just like in the web app - full context, full capabilities, zero friction. Click on “New chat” and type “Langdock” to open a chat with the app.

Channel collaboration with @Langdock
Alternatively, you can pull Langdock into any channel you have (channels for a specific topic, indicated by a main message and thread with replies to this message). The app only reads the entire thread once mentioned with @, to help you with the current topic.

Working with the App in chats
You can also work with the app in chats you have with other users. Here, you can also tag the app with @ and then your prompt. The model can only reference this individual message, but not the entire chat.

Main Features

Selecting your default model
When pulling the app in your chat, you can either use the default model (e.g., GPT-5.1) or select a specific agent. The model is a good default for quick needs like explanations or smaller questions.

Agent selection inside Teams
Start a conversation with any Langdock Agent - from Translators to HR FAQ Agents - directly inside Teams.

File & image support
Upload documents or images in Teams messages - Langdock can read and analyze them just as it does in the web app.

Why we built the Teams App

Many teams use Microsoft Teams to collaborate and communicate with others. Many users have requested a way to use Langdock in Teams, as they already use the app several times a day. Teams becomes a natural extension of Langdock to help your team collaborate faster, and embed Agents into everyday workflows - from shared problem‑solving to specialized channel setups.

How to get started

Your workspace admin can install Langdock from the Teams Admin Center.
After installation, users can simply search for Langdock in the Teams apps.

If you want to dive deeper, check out the setup guide and usage guide.

We’re looking forward to your feedback on this one! 🙌

We're renaming Assistants to Agents across Langdock! This change reflects how the product has evolved and how the market and many of you talk about AI.

What's changing?

Only the name. Your existing assistants keep all their capabilities, configurations, and sharing settings. Everything works exactly as before.

Why Agents?

When we launched Assistants in the summer of 2023, the market was figuring out basic functionality, like how to let AI work with a few documents. Since then, the capabilities have grown significantly. What started as rather simple chatbots can now handle large file collections, work with tabular data, connect to your tools, and much more. They use agentic behavior to choose the right approach and tools for each task, working within the configuration you define.

The term "Agent" has become the industry standard for what we used to call Assistants. Many companies, such as Microsoft and Google Enterprise AI, use this terminology. More importantly, we've heard from many of you over the past months that users are used to the term "Agents" or even ask whether Langdock has agents available.

Why now?

This change comes with the launch of Workflows a few weeks ago. Agents and Workflows are complementary products: Agents are your interactive AI assistants for specific tasks, while Workflows let you chain multiple building blocks together (including multiple agents) to automate larger processes in the background.

What does this mean for you?

No action is required from you! The transition happened automatically, and we've updated all documentation to reflect the new terminology.

The assistant API remains unchanged by these changes for now. There will be a separate notification early next year to communicate the changes.

The Langdock platform now consists of the following products: Chat, Agents, Workflows, Integrations, and API. Renaming a core product isn't something we do lightly. We've thought carefully about this and talked to many of you. Ultimately, it made sense for us given how the product and market have evolved.

We'd love to hear your feedback on how we can continue to improve Agents for you! 🙌

Since launching Workflows a few weeks ago, our team has been working on a lot of improvements and performance upgrades for the product to make the experience smoother and more powerful. As a lot of users have requested, we have focused on making building, testing, and refining your workflows easier than before. Thank you again for all the feedback - see our launch video below!

Here is a list of all major updates:

New node: Loop

Enhance your workflows by automating repetitive actions. Loop nodes allow you to perform a selection of nodes multiple times before moving on to the next node. This helps with repetitive actions or iterating over a list of items.

New node: Generate image

Image generation now also works in workflows. This is perfect for visual automation and creative tasks if you regularly need to generate images. Simply select the ‘Generate Image’ node, and choose your preferred image model to get started!

Re‑run Failed Executions

If something doesn’t go to plan, you can now retry failed runs instantly without restarting the entire workflow.

Custom Webhook Responses

Workflows can now send real‑time replies to incoming requests. This is great for syncing with apps like Slack or notifying other systems instantly.

File Uploads via Webhooks

You can now send files directly into your workflows from external applications, opening up even more integration possibilities.

Sidebar Pinning

Just like you can pin your assistants to the sidebar, we have also implemented pinning for Workflows. Now, you can keep your favourite workflows just a click away!

Workflow Chat Context

You can now personalise the behaviour of your workflow chat by adding your favourite tools, such as Gmail or Outlook, HubSpot or Salesforce, directly as context to the Workflow builder. Simply open the chat and click ‘Set up’ to customise how workflows are built for you.

Customise Workflow Submission Forms

When creating a workflow form, you can now customise the submission experience. Adjust the colour, description, and name of the submission by unfolding the ‘Customisation’ section during form creation.

These improvements can help with simple daily tasks, like reminders or quick research, as well as more complex, multi-step processes. We can’t wait to hear what you think!

We've improved how we process PDFs to better handle visual content.

Until now, when you uploaded a PDF to Langdock, we extracted the text from it and sent it to the AI model, and created so-called “embeddings” to enable the model to perform a semantic search on the PDF. This allows the model to generate qualitative responses based on the uploaded file.

To further improve this processing, we now also take screenshots of pages and provide them to the model. In simple terms, this gives the model “eyes”, so you can now ask questions like “Describe the details of the graphic on page 26" and get accurate answers, since the model can now actually "see" the document content. The model now has a new “view page” tool for inspecting pages, which is particularly helpful for images, charts, logos, and other visual elements.

As always, let us know what you think! 🙌

Anthropic’s Claude Opus 4.5 is now available in Langdock! 🚀

The new model introduces enhanced capabilities for coding, agentic workflows, and handling complex tasks.

Claude Opus 4.5 delivers improvements in reasoning, providing clearer answers with less technical jargon.

You can learn more about the model in Anthropic’s official announcement.

We have automatically enabled Opus 4.5 in all workspaces where Claude Sonnet 4.5 was previously activated.

Like Claude Sonnet 4.5, the model is available in two versions: one with reasoning and one without. This allows you to choose whether you want the model to reason for your current request.

We upgraded GPT-5 and GPT-5.1 to the latest model versions from OpenAI, now featuring a dedicated "Chat" version optimized for conversational interactions.

The new Chat version delivers responses with richer formatting: better structure, clearer lists, and more polished outputs that make conversations easier to follow and act on. These are the same model versions currently used in ChatGPT.

Both GPT-5 and GPT-5.1 "Chat" versions are hosted in the EU. The previous GPT-5 and GPT-5.1 models have been updated and are now live. If you haven't tried out the latest GPT-5 series yet, give it a try!

We are excited to announce that GPT-5.1 is now available in Langdock! 🚀

As of today, we are sharing the newest GPT-5 series release: GPT-5.1, available also in thinking mode. This model improves on both intelligence and communication style.

This model is more intelligent, warmer, and better at following instructions than GPT-5. You may notice a more playful tone, paired with well‑structured outputs.

This model is a great choice when you want it to closely follow your guidance and produce polished responses. It has become faster at solving simple tasks, while being more persistent on complex ones. The model generates clearer responses by focusing on less technical jargon.

You can read more about the launch in the announcement from OpenAI.

Like the previous GPT-5 model, the model is available in two modes - one for fast responses (GPT-5.1) and one for reasoning before responding (GPT-5.1 Thinking).

The model is hosted by Microsoft Azure inside the EU and available to all workspaces now.

We're excited to launch Workflows, a powerful new way to build AI-driven automations in Langdock! 🚀

Workflows bring together everything you already use in Langdock - Chat, Assistants, and Integrations - into end-to-end automations. Think of it as your orchestration layer where you can chain multiple steps together, add conditional logic, loop through data, and create sophisticated processes that run automatically.

What are Workflows?

Workflows allow you to build complex, multi-step automations without writing code. They can be triggered by a form submission, a schedule, or an event in your connected apps and handle entire processes from start to finish-automatically and reliably.

Key capabilities:

• Multi-step automation: Chain assistants, integrations, and custom logic into sophisticated workflows.
• Flexible triggers: Start workflows manually, on a schedule, via webhook, or through form submissions.
• Conditional logic: Add deterministic if/then branches, loops, and decision trees to handle complex scenarios.
• Human-in-the-loop: Include manual approval steps when needed for critical decisions.
• AI at every step: Use different AI models throughout your workflow to analyze, decide, and adapt.
• Cost management: Monitor and control workflow spending with built-in cost limits and usage tracking.

Why Workflows?

More powerful than Chat: While Chat is perfect for interactive conversations, Workflows automate entire processes in the background. Set them up once, and they run reliably 24/7.

More flexible than Assistants: Assistants are great for specific tasks, but Workflows let you combine multiple assistants, add custom logic, integrate with external APIs, and create sophisticated decision trees.

More than Integrations: Integrations connect your apps, but Workflows orchestrate complex processes across those apps-with AI at every step.

Example use cases

• Automatically analyze and route customer support tickets based on content and urgency.
• Generate weekly reports by pulling data from multiple sources, analyzing trends, and distributing results.
• Process form submissions with AI review, conditional approval flows, and automated follow-ups.
• Monitor data sources on a schedule and trigger actions when specific conditions are met.

Getting started

Workflows are available now in Langdock! To start building:

1. Workflows must be activated by an admin in workspace settings.
2. Navigate to the Workflows section in your sidebar.
3. Create your first workflow using our visual builder.
4. Choose a trigger, add nodes, and connect your logic.

Check out our

to get started or our documentation for detailed guides.

Important notes:

• AI usage in workflows is billed via API pricing, and depending on the number of runs, you might need a subscription upgrade (pricing details here).
• Set cost limits and enable monitoring to control spending.
• All workflow executions are logged to the workflow creator for transparency and debugging.

We're excited to see what you build with Workflows! As always, we look forward to your feedback. 🙌

We improved group permissions to allow more intuitive sharing and permission handling around prompts, assistants and knowledge folders within your team.

Until now, all group members, editors and admins were able to share prompts, assistants and knowledge folders with the entire group which often led to cluttered groups and unclear governance.

Most important changes

• From now on, group members can access and use all prompts, assistants, and knowledge folders shared with the group, but cannot share new resources themselves.
• The editor role allows users to contribute to the group by sharing prompts, assistants, and knowledge folders.
• Group admins keep full group management rights.
• New SCIM group settings allow workspace admins to effectively customize role management in synced groups

Why did we change this?

With this update to group role permissions, we reduce clutter in large groups by limiting who can share resources. Moreover, we clearly separate contributing to a group (editor) from managing a group (admin) for cleaner governance.

Detailed permission overview

Members:

• Can see group details and use prompts, assistants, and knowledge folders
• Cannot share to the group

Editors:

• Can do everything members can do
• Can share prompts, assistants, and knowledge folders to the group
• Cannot rename the group or manage members/roles

Admins:

• Can do everything editors can do
• Can change user roles and add/remove users
• Can rename group and change group description
• Can delete group

For more details, also check out our updated documentation page.

How does this affect me?

Sharing flow: You will still see all your groups when sharing prompts, assistants or knowledge folders. If you're an Editor or Admin, you can share with them. If you're a member, the group will be greyed out with an info message explaining why.

Group members were migrated to editors: Users who were members of a group before the update now have the editor role. Since the new editor role has the same sharing permissions as the old member role, nothing changes for previously shared prompts or assistants.

Admin tools and SCIM defaults: We added admin settings and tools that make syncing SCIM groups with these new permissions much easier:

• Set the default role for newly synced SCIM groups in the security settings
• Set the default role for new users added to a specific SCIM group
• Use bulk actions to change the roles of all members or editors in groups

Please check out our documentation here for more details.

We look forward to hearing your feedback on how these new permission levels improve collaboration in your workspace! 🙌

We are excited to announce that Gemini 2.5 Flash Image (Nano Banana) is now available in the EU! 🚀

Google's image generation model has been in high demand since its launch. It is one of the best image generation models right now and also supports editing images.

Unfortunately, it was not available in the EU until now. But Google launched the EU-hosted model recently, so we added the model and enabled it as the default image generation for all workspaces.

The most important highlights are:

• Image editing: Upload images and customize them with prompts – add elements, remove them, change colors, or transform the style
• High image quality: Precise rendering of details and reliable implementation of your creative ideas

You can customize your personal default image model at any time in your account settings under Preferences.

The model is now live, and we look forward to your feedback!

You can now receive important, personalized notifications directly in your inbox, so you never miss an update and always stay on top of what matters.

What’s new?
The new “inbox notifications” feature delivers relevant updates straight to your inbox. With just one click, you can jump directly to the related request or completed result.

When do you receive notifications?

Assistant shared: When someone shares an assistant with you, you’ll get a notification in your inbox with a link to it and details on your access level. This lets you see what’s available and start right away.

Deep Research completed: For longer Deep Research requests, you’ll be notified as soon as the analysis is complete. Perfect for using your time efficiently while working on other tasks in parallel.

Access request (for admins): When a colleague requests access to Langdock, the request will appear directly in your inbox.

We will add many more inbox notifications in the coming months!

You can find the Inbox in the left sidebar, right below the chat search bar. The number of unread messages is highlighted, so you can easily spot them.

We’re looking forward to your feedback on this new feature!

A new generation of image generation models is now available in Langdock!

Until now, DALL-E 3 was the only image model available in Langdock. From now on, you can also access a new generation of powerful image generation models from Black Forest Labs, OpenAI and Google.

Starting today, the following image models are available in Langdock:

Black Forest Labs:

• Flux1.1 Pro Ultra
• Flux.1 Kontext (supports image editing)

Google:

• Imagen 4
• Imagen 4 Fast
• Gemini 2.5 Flash Image (Nano Banana)*

OpenAI:

• GPT Image 1*

The new models offer significantly improved image quality, more precise rendering of details and even better implementation of your creative ideas. With this expanded selection, you can now choose the perfect model for your specific use case and elevate your creative projects in Langdock.

How to use the new models:
To switch between the different image models, you can select the various models via the new button in the chat field and use them to generate images.

If you do not select a specific model, your default image model will be used for all image generation prompts. We have now set Flux1.1 Pro Ultra as the default model, which previously was DALL-E 3. You can choose your standard image model in your Account Settings under Preferences.

We are excited to hear what you think of the new models! 🙌

*These models are currently not available with EU hosting and therefore not enabled by default.

We're excited to announce that Claude Sonnet 4.5 is now available to Langdock users!

Claude Sonnet 4.5 is Anthropic's most advanced model yet. According to several benchmarks, it compares to the GPT-5 models and even surpasses them in some areas. You can read more about the launch in the announcement from Anthropic.

As with the previous versions of Claude Sonnet, we recommend it for coding and creating text, since it has an authentic and realistic tone of voice.

We added two models to give you the choice on whether you want to use reasoning. The models are Claude Sonnet 4.5 and Claude Sonnet 4.5 Reasoning.

We host the models on Google Cloud and AWS in the EU.

The models are live already, and you can test the new Claude version today.

Integrations got a boost ⚡

Since launching our integrations platform, teams have been connecting their core tools to build more capable assistants. With Actions in Chat, you can now run integrations in any conversation.
To make the user experience of working with integrations even more seamless and powerful, we shipped:

• 15 new integrations to unlock more real-world use cases
• 10+ new ready-to-use Assistant Templates using these integrations
• Reliability and UX improvements across our most-used integrations

To get started quickly, duplicate a template, connect your tools, and customize the assistant to your own workflow.

New integrations

1. Asana: Interact with your Tasks, Attachments, Projects, Goals, and more directly from Langdock.
2. Google BigQuery: Create, manage, share, and query on your data.
3. Google Analytics: Generate reports, analyze traffic, and get real-time and content insights.
4. Google Tasks: Manage with you tasks and task lists seamlessly from Langdock.
5. Microsoft Planner: Create and manage plans, tasks, buckets, and comments to organize and track work across your team.
6. AWS Kendra: Search your enterprise data with natural language queries and retrieve index configurations.
7. Stripe: Manage payments, subscriptions, invoices, and financial data for your customers.
8. Personio: Manage and sync employee, HR, and payroll data across your organization.
9. Tableau: List workbooks, extract view data, get view images, and explore your analytics content.
10. Monday.com: Manage boards, track tasks, and collaborate with your team.
11. Miro: Retrieve content from boards, frames, cards, sticky notes, and more.
12. Eleven Labs: Convert text to natural-sounding speech and access conversation transcripts.
13. Statista: Search Statista's huge variety of statistics and get concrete data to visualize in Langdock.
14. Open register: Get access to structured, official German company registry data.
15. Pylon: Manage accounts, teams, issues, and knowledge bases to streamline support operations.