Dust Release Notes

Triggers Now Run Inside Pods

🎯 What is it?

When a trigger fires, the conversation it creates now lives directly inside the Pod you've selected. This means every automated run lands in the right workspace context from the start, rather than sitting outside your team's organized spaces.

💡 Why is it useful?

Automated work can quickly become hard to track when it's scattered outside your team's normal environment. By routing triggered conversations into a Pod, everything stays organized, easy to find, and shareable with the right people — automatically placed where the relevant context already lives.

⚙️ How does it work?

When you set up a trigger, you select the Pod where its conversations should run. From then on, each time the trigger fires, the resulting conversation is created inside that Pod alongside your team's related work.

✨ Concrete Use Cases

Here's how you could use it:

• Recurring reporting: A daily trigger that generates a summary now posts its conversation straight into your team's reporting Pod, where everyone already looks for updates.
• Automated monitoring: A trigger watching for specific events creates its conversations inside the dedicated project Pod, so the whole team can review and act on them in context.

📈 Benefits for you

Less time spent hunting for automated runs, better visibility for your team, and cleaner organization of all triggered work — each conversation lands exactly where it belongs, with the right people able to access it.

🚀 How to access it?

This is available to all users. Simply open your trigger configuration and select the Pod where you'd like the triggered conversations to run.

What is it?

We've added Anthropic's latest model, Claude Sonnet 5, to Dust. The claude-sonnet global agent now runs on Sonnet 5 automatically, and you can also select Sonnet 5 directly when building your own agents.

Why is it useful?

You get access to the newest generation of the Sonnet model — with its improvements in reasoning, quality, and overall performance — without having to change any of your existing setups. The upgrade happens seamlessly behind the global agent.

How does it work?

The claude-sonnet global agent has been updated to point to Sonnet 5, so it's already using the new model. In the agent builder, Sonnet 5 now appears as an option in the model picker, ready to be assigned to any agent you create or edit.

Concrete Use Cases

Here's how you could use it:

• Upgrade an existing agent: Edit one of your custom agents and switch its model to Sonnet 5 to benefit from the latest improvements.
• Quick everyday tasks: Simply use the claude-sonnet global agent — it already runs on Sonnet 5, no configuration needed.

Benefits for you

Access to a more capable model for your agents, improved output quality, and a smooth transition since your current configurations keep working as-is.

How to access it?

If your workspace is on a paid plan, Sonnet 5 is already available — no feature flag required. Use it through the claude-sonnet global agent, or select it in the model picker within the agent builder.

Please note

Sonnet 5 is not yet available for workspaces with EU data residency. We'll keep you informed as soon as that changes.

What is it?

The "Ask user question" capability is now built into every agent by default. This means any agent can pause mid-task to ask you a clarifying question when it needs more information, instead of guessing or proceeding with incomplete instructions. Previously, this had to be manually enabled on a per-agent basis.

Why is it useful?

Until now, this capability was opt-in, which made it hard to discover and easy to forget when building a custom agent. By making it a default for all agents, you get more reliable, conversational interactions out of the box — agents can check in with you before heading in the wrong direction.

How does it work?

When an agent encounters ambiguity or needs a decision from you, it can now ask you directly during a task. You answer, and the agent continues with the right context. No setup or configuration is needed.

Concrete Use Cases

Here's how you could use it:

• Ambiguous requests: You ask an agent to "draft the email to the client" — instead of assuming which client, it asks you to confirm before writing.
• Missing details: An agent working on a report notices a required figure is missing and asks you for it, rather than leaving a gap or inventing a value.

Benefits for you

More accurate results, fewer back-and-forth corrections, and a smoother collaboration with your agents — especially for custom agents where this previously had to be configured manually.

How to access it?

There's nothing to set up. This is now active by default for all agents across your workspace, including any custom agents you've already built.

The Computer: Let Your Agents Work Safely with Files, Code, and More

🎯 What is it?

The Computer is a new capability that gives your agents access to an isolated, secure environment where they can work directly with files, run calculations, execute code and handle larger multi-step workflows. Optionally, you can authorize your Computer environment to make network requests to specific destinations.

💡 Why is it useful?

Until now, agents were limited when it came to tasks that required actually processing files, running code, or chaining together more complex operations. The Computer removes those limits by giving agents a safe, sandboxed space to get hands-on work done, so they can support richer and more demanding tasks end to end.

⚙️ How does it work?

Agents operate inside an isolated environment where they can safely manipulate files, perform computations, run code, and connect to external resources. Because the environment is sandboxed, this work happens securely without affecting your other systems. This also unlocks support for most external agent skills.

✨ Concrete Use Cases

Here's how you could use it:

• File processing: Have an agent extract text from a PDF, clean up a spreadsheet, or convert and reorganize a set of documents.
• Calculations & data work: Ask an agent to run numerical analysis or process a dataset and return the results.
• Code execution: Let an agent write and run code to automate a task or test a quick script.
• Larger workflows: Combine several steps, such as fetching data via a network request, transforming it, and producing a final output, in a single agent run.

📈 Benefits for you

More powerful agents and more efficient workflows. Tasks that previously required manual effort or couldn't be handled at all can now be completed directly by your agents, with broader support for external agent skills.

🚀 How to access it?

The Computer is available to everyone, with one exception: Enterprise workspaces that were not part of the beta. If that's your case, you can opt in at any time, and every workspace will automatically receive the feature within the next 2 weeks. You can learn more in the documentation.

Pods Now Apply Your AGENTS.md to Every Conversation

🎯 What is it?

Pod editors can now manage an AGENTS.md file directly from their Pod settings. Once set, Dust automatically adds its content to the system prompt of every conversation that happens within that Pod, so your guidelines and workflows are always in effect.

💡 Why is it useful?

Previously, keeping behavior consistent across multiple conversations often meant copy-pasting the same instructions over and over. This feature lets you define your Pod-level rules and workflows once, in a single place, and have them applied everywhere automatically—ensuring consistency across every run without the manual overhead.

⚙ How does it work?

Editors update the AGENTS.md file from the Pod settings, and Dust injects it into the system prompt for all conversations in that Pod. Oversized files are now handled more safely, so large instruction sets won't cause issues.

✨ Concrete Use Cases

Here's how you could use it:

• Consistent tone and formatting: Define how agents should respond (language, style, structure) so every conversation in the Pod follows the same standards.
• Shared workflows and guardrails: Document the steps, do's and don'ts, or compliance rules your team must follow, and have them automatically enforced in each conversation.

📈 Benefits for you

You save time by setting your rules once instead of repeating them, you reduce the risk of inconsistent behavior across conversations, and you gain a single, easy-to-maintain source of truth for how your Pod should operate.

🚀 How to access it?

This is available to all Pod users for Pod conversations—no feature flag required. Pod editors can simply open their Pod settings and edit the AGENTS.md file to get started.

Adomik Integration: Ad Revenue Analytics & Knowledge, Directly in Dust

What is it?

Adomik is now available as a default integration in Dust, connected securely via OAuth. Once enabled, your builders can give agents read-only access to Adomik's tools, allowing them to analyze your programmatic advertising and monetization data, as well as search and retrieve pages from your Adomik knowledge base, all without leaving Dust.

Why is it useful?

If your teams work with programmatic advertising, investigating revenue movements or pricing shifts often means jumping between tools and manually pulling reports. This integration brings that data and knowledge directly into your agents, so you can run monetization investigations and draft analyses in one place.

How does it work?

Adomik connects as a remote integration through a secure OAuth login. The tools are strictly read-only, meaning agents can analyze and retrieve your data but cannot modify anything on the Adomik side.

Concrete Use Cases

Here's how you could use it:

• Revenue investigation: Ask an agent to identify and explain sudden CPC/CPM shifts or revenue movements across your programmatic inventory.
• Report drafting: Have an agent pull the relevant monetization figures and draft a first version of a performance report for your team.
• Knowledge lookup: Let an agent search your Adomik knowledge base to quickly answer process or methodology questions.

Benefits for you

You save time by consolidating ad data analysis and knowledge retrieval into your existing Dust agents, reduce manual back-and-forth between platforms, and give your teams faster, data-backed answers on monetization questions.

How to access it?

An admin first connects Adomik from Spaces → Tools. Once connected, your builders can add the Adomik tools to any relevant agent.

What is it?

The Lemlist MCP Server is now available across all Dust workspaces. It connects your Dust agents directly to Lemlist, giving them access to your leads, verified contacts, and multichannel outreach sequences. In short, your agents can now help you manage your outbound workflow without you having to switch tools.

Why is it useful?

Outbound prospecting often means juggling several tools and repeating the same manual steps: pulling lead lists, checking contact details, updating sequences. By bringing Lemlist into Dust, you can hand those tasks to an agent and keep your focus on strategy and conversations that matter.

How does it work?

Once enabled, an agent can query and act on your Lemlist data through the connection: retrieving leads, accessing verified contact information, and working with your multichannel sequences. You simply ask the agent in natural language, and it interacts with Lemlist on your behalf.

Concrete Use Cases

Here's how you could use it:

• Lead review: Ask an agent to pull a list of leads from a given Lemlist campaign and summarize who's worth prioritizing.
• Contact enrichment: Have an agent retrieve verified contact details for a set of prospects before you reach out.
• Sequence management: Ask an agent to check the status of your multichannel sequences or help you organize prospects across channels.

Benefits for you

Less tool-switching, faster access to your outbound data, and the ability to delegate repetitive prospecting tasks to an agent. The result is a smoother outbound workflow and more time for high-value selling.

How to access it?

The Lemlist MCP Server is available in all Dust workspaces. You can add it as a tool when building or editing an agent, then connect your Lemlist account to start using it. If you're a Lemlist user, it's ready for you to set up today.

Why is it useful?

GLM 5.2 is a new AI model developed by the lab Z.ai, now available within Dust. It performs at a frontier level on many agentic benchmarks, with results comparable to leading models like Opus 4.8 and GPT 5.5. The model is hosted in the United States by Fireworks.

Having access to a broad range of high-performing models means you're never locked into a single provider. GLM 5.2 expands your options with a model that delivers top-tier performance on agentic tasks, giving you more flexibility to choose the right model for your specific needs and use cases.

How does it work?

GLM 5.2 is available as a model option when building or configuring your agents. You simply select it from the list of available models, just as you would with any other supported model. Although developed by Z.ai, it is hosted in the US by Fireworks.

Concrete Use Cases

Here's how you could use it:

• Agentic workflows: Power agents that handle multi-step tasks and tool use, where GLM 5.2's strong agentic benchmark performance shines.
• Model comparison: Test GLM 5.2 against your current models on your own use cases to see which delivers the best results for your team.

Benefits for you

More choice, more flexibility. You gain access to an additional frontier-level model, allowing you to optimize your agents for performance while diversifying beyond a single model provider.

How to access it?

GLM 5.2 is now available in the model selection menu when creating or editing an agent. Simply choose it as your model to start testing it on your workflows.

Email Threads Now Stay in a Single Conversation

📌 Context

When you interact with a Dust agent over email, each reply used to start a brand-new Dust conversation. So if an agent answered your email and you replied back, that reply was treated as a separate, disconnected conversation, losing the continuity of the exchange.

We've changed this behavior: an email thread now maps to a single Dust conversation. Every reply within the same email thread continues in the same conversation, preserving the full context of the discussion. This change was driven both by product best practices and by popular demand from users.

🔄 Impact on Dust

Dust now recognizes when an incoming email belongs to an existing thread and routes it to the matching conversation automatically. The agent keeps the full history of the exchange in context, so each reply builds on what came before rather than starting from scratch.

👤 Impact for you

This is a positive change with no downside. When you email back and forth with an agent, the conversation stays coherent: the agent remembers the earlier messages in the thread, giving you more relevant and context-aware responses. You no longer end up with a scattered set of one-off conversations for what is really a single discussion.

✅ Actions required

No action required on your part. The improvement is live and applies to everyone automatically. Just reply within the same email thread as usual, and the conversation will continue seamlessly.

What is it?

Your agents can now connect directly to Clari Copilot to search and analyze your sales calls. Without leaving Dust, an agent can pull up call transcripts, AI-generated summaries, discussed topics, action items, and competitor mentions. You can also filter calls by attendee email to zero in on specific conversations.

Why is it useful?

Sales call intelligence usually lives in a separate tool, which means manually exporting or copy/pasting transcripts whenever you want to act on them. This integration removes that friction: the insights captured in your calls become directly usable inside your Dust workflows, so nothing gets lost between the conversation and the follow-up.

How does it work?

Dust connects to Clari Copilot through a dedicated integration secured with your Clari API credentials. Once connected, your agents can query call data on demand, just like they would search any other connected source.

Concrete Use Cases

Here's how you could use it:

• Account recaps: Ask an agent to summarize all recent calls with a given account before a renewal conversation or QBR.
• Sales-to-CS handoffs: Generate a clean handoff brief from the latest sales calls, including action items and key topics, so Customer Success starts fully informed.
• Meeting follow-ups: Draft follow-up emails based on what was actually said and committed to during a call.
• Voice of Customer analysis: Surface recurring themes and competitor mentions across calls to feed product and go-to-market decisions.

Benefits for you

Less manual exporting and copy/pasting, faster and more accurate follow-ups, and smoother handoffs between teams. Your call data stops being a static archive and becomes something your agents can act on in real time.

How to access it?

The integration is now generally available to all workspaces. To set it up, add the Clari Copilot MCP server in your workspace tools and configure it with your Clari X-Api-Key and X-Api-Password. Once connected, you can add the Clari Copilot tools to any agent. Reach out to us if you'd like a hand getting it configured.

What is it?

Dust can now be connected to any MCP-capable client as a remote MCP server. This means you can access your Dust building blocks—workspace knowledge, Pods, conversations, and files—directly from the other tools you already use, without having to open Dust itself.

Why is it useful?

Until now, reusing your Dust knowledge and artifacts in another tool often meant copy/pasting content back and forth or constantly switching between apps. By making Dust available as a remote MCP server, your trusted context travels with you, so the same knowledge and outputs can be tapped into wherever you work.

How does it work?

MCP (Model Context Protocol) is a standard way for applications to securely connect to external sources of context. Any client that supports MCP can now authenticate to Dust and pull in your building blocks on demand. Full setup instructions are available in the documentation.

Concrete Use Cases

Here's how you could use it:

• Working in an MCP-capable coding or writing tool: Pull in relevant workspace knowledge or a past conversation directly into your working environment, without leaving the app you're in.
• Reusing existing artifacts: Reference files or Pod content from Dust inside another client, so your team relies on a single, trusted source instead of duplicated copies.

Benefits for you

Less copy/pasting, fewer app switches, and more consistency. Your teams can reuse the same trusted knowledge and artifacts across tools, which saves time and reduces the risk of working from outdated or fragmented information.

How to access it?

This is available now to everyone—no feature flag required. To get started, follow the connection steps in the documentation.

A note for workspace admins: you stay in control of access. You can disable MCP server access for the entire workspace, and you can restrict which redirect URIs are allowed during client authentication.

Gamma is now available as a Remote MCP Server in Dust

🎯 What is it?

You can now connect Gamma to Dust as a Remote MCP Server. This lets your Dust agents generate—and read—Gamma decks, documents, and webpages directly using the context already available in your workspace. The result is a ready-to-polish Gamma artifact you can refine and share.

💡 Why is it useful?

Building a presentation usually means gathering research, notes, and context, then manually copying everything into a slide tool. This connection removes that back-and-forth: your agent takes the context it already has and turns it into a structured Gamma deck for you, so you can focus on refining the final output rather than assembling it from scratch.

⚙ How does it work?

Once Gamma is connected as a Remote MCP Server in your workspace, your agents can call it to create or read Gamma content. You ask the agent to build a deck (or doc/webpage), and it produces a Gamma artifact you can then open and polish in Gamma.

✨ Concrete Use Cases

Here's how you could use it:

• Client-ready proposals: Have an agent compile your research and meeting notes into a first-draft Gamma deck, ready for you to tailor before sending.
• Internal updates: Turn a body of context—project notes, status updates, data—into a structured presentation or webpage without manual slide-building.

📈 Benefits for you

You save time by skipping the copy/paste shuffle, move faster from raw context to a polished draft, and keep your presentations grounded in the information already living in your Dust workspace.

🚀 How to access it?

This feature is generally available to everyone with a Gamma account. To get started, connect Gamma as a Remote MCP Server in your workspace, then ask one of your agents to generate a Gamma deck, document, or webpage.

What is it?

You can now reference skills and tools directly inside your skill instructions, the same way you already reference knowledge. Skills can call on other skills, letting you build richer, more modular capabilities by combining existing building blocks. As part of this change, the separate "tools" section has been removed, and tools are now inserted inline wherever you need them.

Why is it useful?

Until now, skills stood on their own and couldn't draw on one another, which often meant duplicating the same logic across multiple skills. This update responds to a widely requested ability to compose skills, so you can assemble specialized capabilities into more complete workflows without rebuilding them each time.

How does it work?

When editing a skill's instructions, you simply use a dropdown to insert a reference to another skill or to a tool inline, exactly as you would when adding knowledge. The referenced skill or tool becomes part of that skill's behavior, so capabilities can be layered and reused.

Concrete Use Cases

Here's how you could use it:

• Building on existing skills: Create a "Weekly Report" skill that references your existing "Data Retrieval" and "Summarization" skills, rather than duplicating that logic.
• Inline tool placement: Insert a specific tool exactly at the point in your instructions where it's needed, making the skill's behavior clearer and easier to maintain.

Benefits for you

Less duplication, easier maintenance, and far more flexibility when designing skills. By composing skills from smaller, reusable pieces, you can build sophisticated agents faster and keep them consistent over time.

How to access it?

The feature is available to everyone. When editing a skill, use the dropdown within the instructions to insert a reference to another skill or a tool. Your existing skills have already been updated automatically: the list of tools previously associated with a skill now appears at the top of its instructions, so nothing is lost in the transition.

No action is required on your part, your existing skills continue to work as before. This is simply a new way to compose and reuse them going forward.

Dust Support: Get Instant, Grounded Support Answers from @dust

🎯 What is it?

We've introduced a new discoverable skill that turns @dust into your first line of support. When you ask a support-related question, the agent detects your intent, answers it directly, and grounds its response in trusted sources so you can rely on what it tells you.

💡 Why is it useful?

Until now, getting a support answer often meant leaving your workspace to search documentation, browse community threads, or file a request and wait. This skill brings accurate support answers to you instantly, right where you already work, so you spend less time hunting for help and more time getting things done.

⚙️ How does it work?

The skill recognizes when you're asking a support question and responds with answers grounded in real, up-to-date sources: the public dust-tt/dust GitHub issues and the Dust community. This means responses reflect documented known issues and community knowledge rather than guesswork.

✨ Concrete Use Cases

Here's how you could use it:

• Troubleshooting a behavior: Ask "Why is my agent not picking up the latest documents from my connected data source?" and get an answer grounded in known issues and community discussions.
• Checking a known issue: Ask "Is there a reported problem with PDF parsing right now?" and find out whether it's a documented issue with a workaround or fix already discussed.

📈 Benefits for you

Faster, more accurate answers without leaving Dust. You get reliable support grounded in real sources, reduce the back-and-forth of opening tickets, and resolve questions in the flow of your work.

🚀 How to access it?

The skill is discoverable and available to every user. Simply mention @dust and ask your support question. The agent will detect that you need support and respond with a grounded answer.