🎯 What is it?

You can now type / directly in the conversation input bar to quickly access and add capabilities to your conversations. A searchable dropdown appears instantly, listing all available skills and MCP tools, which you can filter and select using your keyboard or mouse.

💡 Why is it useful?

Previously, accessing capabilities required navigating through the toolbar, which could interrupt your workflow. This new slash command feature streamlines the process, letting you stay focused on the conversation while quickly adding the tools you need—similar to how modern text editors and communication tools work.

⚙ How does it work?

Simply type / in the input bar, and a dropdown menu appears with all your available capabilities. Continue typing to filter results using fuzzy matching (you don't need to type exact names), then select what you need with your keyboard (arrows, Enter, Tab) or mouse. Press Escape to close the menu.

✨ Concrete Use Cases

Here's how you could use it:

• Quick data analysis: Type / then "calc" to instantly find and add calculator or data processing tools without breaking your thought process

• Adding specialized skills mid-conversation: Type / then start typing a skill name like "research" to quickly enable research capabilities when you realize you need them

📈 Benefits for you

This feature saves time and keeps you in flow. Instead of moving your cursor to the toolbar, you can access everything through keyboard shortcuts, making conversations with agents faster and more efficient—especially valuable when you're working through multiple tasks quickly.

🚀 How to access it?

The feature is available to everyone right now. Just type / in any conversation input bar to try it out.

🎯 What is it?

OpenAI's latest model, GPT 5.5, is now available on Dust. You can select it when building custom agents or use it directly through the global agent interface.

💡 Why is it useful?

GPT 5.5 represents OpenAI's newest advancement, offering improved performance over the previous GPT 5.4 model. This means better reasoning, more accurate responses, and enhanced capabilities for your agents.

✨ Concrete Use Cases

Here's how you could use it:

• Enhanced analysis agents: Build agents that handle complex research, data analysis, or strategic planning with improved reasoning capabilities

• Improved conversational agents: Create customer-facing or internal support agents that provide more nuanced and accurate responses

📈 Benefits for you

Access to cutting-edge AI technology means your agents can deliver higher quality outputs, handle more sophisticated tasks, and provide better assistance to your team.

🚀 How to access it?

• For custom agents: Open the agent builder and select "GPT 5.5" from the model dropdown menu

• For quick tasks: Use the global agent which now runs on GPT 5.5 by default

🎯 What is it?

OpenAI has released GPT Image 2, a new image generation model that's now the default for all image creation on Dust. This model brings significant improvements in image quality, detail rendering, and the ability to accurately generate readable text within images.

💡 Why is it useful?

Previous image generation models often struggled with two key challenges: editing existing images effectively and incorporating clear, readable text into generated visuals. GPT Image 2 addresses both of these limitations, opening up new possibilities for creating professional-quality images that include precise text elements—something that was previously difficult or impossible to achieve consistently.

⚙️ How does it work?

GPT Image 2 is automatically used whenever you generate images through Dust agents or workflows. The model excels at understanding complex prompts, maintaining high fidelity to your specifications, and rendering fine details with unprecedented precision.

✨ Concrete Use Cases

Here's how you could use it:

Marketing Materials: Generate branded images with company names, slogans, or product descriptions clearly visible and professionally rendered—perfect for social media posts, presentations, or campaign materials.

Data Visualization Enhancement: Create infographic-style images with charts, labels, and annotations that include actual readable data points and explanations, making complex information more accessible.

Image Editing & Iteration: Take existing images and ask your agent to modify specific elements while preserving the overall composition—useful for refining visual assets or creating variations of existing designs.

📈 Benefits for you

You can now generate more professional, production-ready images directly within your Dust workflows. The ability to include clear text eliminates the need for post-processing in external design tools, saving time and streamlining your creative processes. The improved editing capabilities also mean you can iterate on images more efficiently.

🚀 How to access it?

No action needed—GPT Image 2 is already the default image generation model on Dust. Simply continue using image generation in your agents as you normally would to automatically benefit from these improvements.

🎯 What is it?

Agents can now proactively pause and ask you structured questions mid-conversation when they need clarification. Instead of guessing or making assumptions, they'll present you with single or multi-select options to help guide their next actions.

💡 Why is it useful?

Until now, when an agent faced ambiguity, it would either guess (sometimes incorrectly), take a random path, or get stuck trying to interpret unclear instructions. Now, agents can simply ask you directly—turning uncertainty into a quick, interactive exchange. This prevents wasted time, reduces errors, and makes conversations feel more collaborative and intuitive.

⚙️ How does it work?

When an agent needs input to proceed, it will pause and present you with a clear question and predefined answer options (single-choice or multiple-choice). You select your answer, and the agent continues with exactly the information it needs.

✨ Concrete Use Cases

Here's how you could use it:

Research workflow: You ask an agent to "analyze our competitors." Instead of picking arbitrary companies, it asks: "Which competitors should I focus on?" with options like [Company A, Company B, Company C, All of the above].

Content formatting: You request a report summary. The agent asks: "What format do you prefer?" with options like [Bullet points, Paragraph form, Executive summary].

Data prioritization: You ask for insights from multiple sources. The agent clarifies: "Which data sources should I prioritize?" offering [Internal reports, Public data, Customer feedback, All sources].

📈 Benefits for you

• More accurate outputs: Agents work with your explicit input instead of assumptions

• Faster resolution: No back-and-forth to correct misunderstandings

• Better control: You guide the agent's direction at key decision points

• Richer interactions: Conversations feel more natural and collaborative

🚀 How to access it?

This feature is available by default for all agents on Dust and Deep Dive, and works seamlessly in Slack conversations as well. No configuration needed—your agents will automatically ask questions when they need clarification.

🎯 What is it?

Workspace admins can now configure Dust conversations to be private by default. When this setting is enabled, conversation URLs are only accessible to participants—anyone else who tries to access the link will see a 404 error, ensuring the conversation's existence isn't even revealed to non-participants.

💡 Why is it useful?

This feature addresses the risk of accidentally sharing sensitive conversations through URLs. While Dust conversations are powerful collaboration tools, sometimes conversation links get shared unintentionally (in Slack, email, or screenshots). With private-by-default URLs, you get an extra layer of protection against accidental leakage while maintaining flexibility when you explicitly need to share.

⚙️ How does it work?

When a workspace admin enables this setting, all new conversations automatically become private—only people directly participating can access them via URL. Participants can still use @mentions to invite others to join conversations, and if needed, anyone in the conversation can flip it back to "accessible to workspace members" from the conversation menu.

✨ Concrete Use Cases

Here's how you could use it:

HR and sensitive discussions: When discussing performance reviews, salary negotiations, or confidential employee matters, conversations stay strictly between participants even if someone accidentally copies the URL.

Strategic planning: When working on confidential product launches, M&A discussions, or competitive analysis with a small team, you can ensure the conversation doesn't leak to the broader workspace if a link is shared out of context.

📈 Benefits for you

• Enhanced security: Reduce the risk of sensitive information leakage through shared URLs

• Peace of mind: Know that conversations stay private unless you explicitly choose to share them

• Flexible control: Keep the ability to make specific conversations workspace-accessible when collaboration requires it

• Maintain collaboration: @mentions still work seamlessly, so you can invite people without compromising privacy

🚀 How to access it?

Workspace admins can enable this feature by navigating to Admin → Workspace Settings and toggling the private-by-default conversation URLs setting. Once enabled, all new conversations will be private by default, while participants can override this on a per-conversation basis from the conversation menu.

🎯 What is it?

You can now import skills directly into Dust from a GitHub repository or by uploading a .zip file from your computer. This new capability gives you more flexibility in how you manage and deploy your skills across your workspace.

💡 Why is it useful?

If you're managing multiple skills or working with a team that maintains skills in a version control system, you previously had to manually copy and paste code into Dust. This new import feature allows you to centralize your skills in GitHub (or any other repository) and keep them in sync with your CI/CD pipeline, ensuring your Dust agents always use the latest versions.

⚙ How does it work?

Simply provide a GitHub repository URL or upload a .zip file containing your skill files. Dust will import the skill structure and make it available in your workspace.

✨ Concrete Use Cases

Here's how you could use it:

Development teams maintaining shared skills: Your engineering team maintains a repository of company-specific skills (e.g., data formatting, internal API integrations). When you update the skill in GitHub, you can quickly re-import it to Dust to keep all agents synchronized.

Distributing skills across workspaces: You've built a powerful skill for market research and want to deploy it across multiple Dust workspaces (different departments or clients). Export it once as a .zip and import it wherever needed.

📈 Benefits for you

• Version control: Keep your skills in Git alongside your other code, with full history and collaboration features

• Automation: Integrate skill updates into your existing CI/CD workflows

• Portability: Easily share and duplicate skills across workspaces without manual copying

• Consistency: Ensure all team members are using the same version of your custom skills

🚀 How to access it?

This feature is available to everyone. When creating or updating a skill, look for the new import options that allow you to specify a GitHub repository URL or upload a .zip file.

🎯 What is it?

Steering transforms how you interact with Dust agents by allowing you to send messages while the agent is working. You can now see every step of the agent's work in real-time—thinking, tool calls, searches—and redirect it on the fly without canceling or losing progress. Additionally, messages are now scoped to one agent at a time, displayed in the input bar, so you no longer need to use @mentions.

💡 Why is it useful?

Previously, conversations with agents were strictly turn-based: you'd send a message, wait for the complete response, and only then could you course-correct if needed. This made it difficult to guide the agent early when you saw it heading in the wrong direction, and you had no visibility into what was happening behind the scenes. Steering solves this by letting you shape the output as it's being built, not after it's done.

⚙ How does it work?

As soon as an agent starts working, you'll see live updates of each step it takes. If you notice it's going off track or you want to add context, simply send a new message—the agent will incorporate your input immediately without restarting from scratch.

✨ Concrete Use Cases

Here's how you could use it:

Research and analysis: You ask an agent to research a topic, but after seeing the first few searches, you realize you need a different angle. Instead of waiting for the full response, you immediately steer it: "Actually, focus on European regulations instead."

Data exploration: An agent starts querying multiple data sources, and you see it's pulling from the wrong database. You send a quick message to redirect it before it completes unnecessary work, saving time and getting accurate results faster.

📈 Benefits for you

• Save time: Redirect agents early instead of waiting for full responses you'll need to regenerate

• Better control: Guide the conversation dynamically based on what you see happening

• Full transparency: Understand exactly what the agent is doing at each moment

• Smoother workflow: No more @mentions needed when working with a single agent

🚀 How to access it?

Steering is now available to everyone automatically. Start a conversation with any agent and try sending a follow-up message while it's working. For complete details and examples, visit the full documentation.

🎯 What is it?

The Dust browser extension is now officially available on Firefox! You can install it directly from the Firefox Add-ons store and enjoy the same seamless Dust experience across all major browsers.

💡 Why is it useful?

Many of you use Firefox as your primary browser, and until now, the Dust extension was only available on Chromium-based browsers. We've expanded our support to ensure all teams can access Dust's capabilities directly from their preferred browser, regardless of which one they use.

⚙ How does it work?

Simply visit the Firefox Add-ons store and install the Dust extension. Once installed, you'll have quick access to your agents and Dust features right from your browser toolbar, just like on Chrome or Edge.

✨ Concrete Use Cases

Here's how you could use it:

For Firefox users: Finally get the same browser integration your Chrome-using colleagues have been enjoying—quick access to agents, easy content sharing, and seamless workflows without switching browsers.

For mixed-browser teams: Ensure everyone on your team can use Dust extension features regardless of their browser preference, making collaboration more consistent and inclusive.

📈 Benefits for you

• Browser flexibility: Use Dust on Firefox, Chrome, Edge, or any Chromium-based browser

• Consistent experience: Same features and functionality across all supported browsers

• No workflow changes: Firefox users can now integrate Dust into their daily browsing without switching browsers

🚀 How to access it?

Visit the Firefox Add-ons store: https://addons.mozilla.org/en-US/firefox/addon/dust/ and click "Add to Firefox". The extension will be ready to use immediately after installation.

🎯 What is it?

We've expanded our Microsoft Teams integration with two new capabilities: agents can now list your Teams meetings and retrieve their transcripts directly within Dust. This means your meeting content is now accessible to your agents, just like your other connected data sources.

💡 Why is it useful?

Meeting discussions contain valuable information—decisions made, action items assigned, key insights shared—but this knowledge often stays locked in transcript files or requires manual review. By making transcripts accessible to your agents, you can automatically extract value from your meetings without manual work.

⚙️How does it work?

Once your workspace admin reconnects the Microsoft Teams tool (to approve the new permissions), agents can access meeting transcripts using two new tools: one to list meetings, and another to retrieve transcript content when available.

✨ Concrete Use Cases

Here's how you could use it:

Meeting Follow-up Agent: Create an agent that reviews your leadership team's weekly sync, extracts action items, and sends a summary to relevant stakeholders automatically.

Cross-team Knowledge Capture: Build an agent that monitors product planning meetings, identifies feature decisions and requirements, and updates your product documentation or project tracker.

Personal Meeting Assistant: Set up an agent that summarizes all your meetings from the past week, highlighting decisions you participated in and tasks assigned to you.

📈 Benefits for you

• Save time: No more manual note-taking or transcript review

• Capture knowledge: Turn meeting discussions into searchable, actionable insights

• Enable new workflows: Automate meeting follow-ups, summaries, and action item tracking

• Connect the dots: Let agents reference meeting decisions alongside your other company knowledge

🚀 How to access it?

Action required: A workspace admin must reconnect the Microsoft Teams tool in your Dust workspace to approve the new permissions (OnlineMeetings.Read and OnlineMeetingTranscript.Read.All). Once reconnected, the new meeting transcript tools will be available to all agents in workspaces using Microsoft Teams.

🎯 What is it?

You can now invite specific people to view a Frame by sending them an email invitation. Recipients receive a direct link to access the Frame, even if they're not part of your Dust workspace.

💡 Why is it useful?

Previously, Frame sharing was all-or-nothing at the workspace level. This new capability gives you granular control over who can see your Frames, making it much easier to collaborate with specific stakeholders, partners, or team members. You can also track who has viewed your Frame.

⚙ How does it work?

When sharing a Frame, you can now enter email addresses of people you want to invite. Each person receives an email with a secure link to access that specific Frame. This respects your workspace sharing policy settings.

✨ Concrete Use Cases

Here's how you could use it:

Executive reporting: Share a sales dashboard Frame with your CEO and CFO without giving them access to all workspace Frames.

Client presentations: Send a project status Frame directly to external clients or partners for review, while keeping other internal Frames private.

Cross-team collaboration: Share specific data visualizations with stakeholders from other departments who need visibility on just that information.

📈 Benefits for you

• Precise control: Share Frames on a need-to-know basis instead of workspace-wide

• Better collaboration: Work seamlessly with external partners and selective internal stakeholders

• Visibility tracking: See who has actually viewed your Frame

• Time-saving: No more screenshots or manual exports—just send a direct link

🚀 How to access it?

This feature is now available to everyone. When viewing any Frame, look for the sharing options and select "Invite by email" to start sharing with specific people.