Dust vs IBM watsonx Orchestrate (2026)

Dust offers more than 70 ready made MCP connectors that let agents use other systems' tools. MCP servers, native and remote, are on both plans, with up to 5 remote servers on Business and no limit on Enterprise. Alongside MCP, Dust maintains native connectors to more than 20 data sources, among them Slack, Notion, GitHub, Google Drive, Confluence, Zendesk and Salesforce, with up to 3 on Business and no limit on Enterprise. The native connectors cover the main systems and MCP covers the rest.

Agents act as well as read, and credits are charged for tool use that includes actions in connected apps. Zapier, Make, n8n and Power Automate are available on both plans. Each integration belongs to a Space, so what an agent can reach through it follows the customer's own access model, not a blanket service account. Dust's inbound APIs, for outside systems calling Dust, are separate. The 70 and 20 counts are Dust's own, with no published directory listing them.

Sourcedust.tt/home/product, /home/pricing feature table and credits FAQread 2026-09-12

Tools are implemented and called by agents to invoke external APIs and services, a tool node places a tool inside an agentic workflow, and the ADK covers tool definition, connections to external systems with their own credential and OAuth token handling, an OpenAPI plugin and MCP based workflows.

Sourceibm.com/products/watsonx-orchestrate/developersread 2026-09-17

Multi agent orchestration with scheduled and event driven triggers is included on both plans, and agents run on those schedules and triggers without a person present. Pods are persistent shared workspaces where people and agents work together on a topic, project or initiative, with shared conversations, tasks, files and agents in one place. Frames are interactive dashboards and apps that agents produce. Pods and Frames run on a shared virtual computer and automations.

Work is built from reusable, governable skills, agents and memory that the customer combines into workflows that compound with use. Deep research tasks that need complex, multi step orchestration and tool use consume more credits. A run can involve the people in a Pod, agents working in parallel, the connected systems each step reads and writes, and the model chosen for each agent. Dust does not say what happens when a step in a multi agent run fails or whether it is retried.

Sourcedust.tt/home/pricing feature table and /home/productread 2026-09-12

Agentic workflows are assembled from node types, including an agent node that hands a step to another agent, branch, parallel, foreach and decision nodes, a script node, a timer node that sets a delay between actions, and a user activity node. Builders work with the Agent Development Kit for pro code control, Langflow for visual design and Flow Builder for rapid orchestration, with branching logic and long running flows.

Sourceibm.com/products/watsonx-orchestrate/developersread 2026-09-17

Scheduled and event driven triggers come with multi agent orchestration on both Business and Enterprise, and automations help power Pods and Frames. Dust's own connectors sync in real time, so a change in Notion, Slack or GitHub reaches Dust without waiting for a poll, and an agent can be triggered by it.

Agents are reached in the Dust workspace, including Pods where people and agents work in parallel, through a Chrome extension that brings agents into the tools people use, and through Slack, Notion, GitHub and Drive. Zapier, Make, n8n and Power Automate are included on both plans and can start a Dust agent from anything they can see. Dust does not list which event types each connector supports or whether customers can combine conditions, and does not explain its automations further.

Sourcedust.tt/home/pricing feature table, /home/product and docs.dust.tt welcome pageread 2026-09-12

Agentic workflows and agents can be scheduled to run automatically at specific times or intervals once schedulable is set on the workflow or agent, with the platform handling cron patterns, timezones and execution limits and the schedule running without manual intervention, and separately each channel a buyer configures (web chat, Twilio WhatsApp, Twilio SMS, Slack, Genesys Bot Connector, Facebook Messenger, Microsoft Teams) provides its own event URL to receive messages.

Sourcedeveloper.watson-orchestrate.ibm.com/scheduling/overview.mdread 2026-09-17

Agents answer through retrieval augmented generation over a corpus Dust keeps current. Dust maintains its own connectors instead of relying on a generic integration provider, and real time sync keeps agents working from current information. Search, query and extraction across all company data are included on the plans. Semantic search covers unstructured content, and Table Query combines semantic search with SQL for structured data, so one run can answer a numeric question from a warehouse and a policy question from a wiki. Image analysis is also supported.

What an agent can retrieve is limited by the asking user's permissions, because data sits in Spaces with configurable access controls and each integration belongs to a Space. Named sources include Slack, Notion, Google Drive, Confluence and GitHub, with more than 20 native connectors in all and anything else over MCP. Dust does not describe chunking, embedding, citations back to a source passage or how fresh a retrieved answer is.

Sourcedocs.dust.tt welcome page with dust.tt/home/product and /home/pricingread 2026-09-12

Agents use knowledge bases to search and return grounded content. Knowledge bases are defined in YAML or JSON and imported through the ADK CLI, in two forms: built-in, backed by a Milvus instance and populated with documents the customer imports, or external, pointing at the customer's own Milvus or Elasticsearch instance.

Sourcedeveloper.watson-orchestrate.ibm.com/knowledge_base/overview.mdread 2026-09-17

Agents can keep a memory of each person they work with. Once the Memory tool is added in the builder, the agent decides during a conversation what is worth keeping, and a user can also ask it to remember something, such as a preference for morning meetings.

Memories are private to each user and kept separately for each agent, they last until the user deletes them, and the user can browse them in the agent's Memory tab and delete any single item.

Within a piece of work, Pods hold the shared conversations, tasks and files for a project, and long conversations are compacted so the agent keeps the thread.

Sourcedocs.dust.tt Agent Memory, Tools and Context Compaction pagesread 2026-10-21

The Agentic SDK ships memory APIs that persist user information and retrieve it during later agent execution, against /memories and /memories/search endpoints: add_messages writes, search, list and retrieve read, and delete and delete_all remove, with memories typed (for example preference), tagged with metadata, scoped by agent and run, and carrying a sensitivity classification.

Sourcedeveloper.watson-orchestrate.ibm.com/sdk/memory.mdread 2026-09-17

Agents stop and wait for a person before an action that needs approval. Every tool on an MCP server carries a stake level, set in its Tools and Stakes settings, and a tool that asks pauses the agent until the user approves or declines that action, with medium stake approvals remembered per agent. Dust's own connectors come with the gate built in for changes, so publishing or deleting in Contentful, writing to Grafana, changing an Airbyte sync or running a paid Bright Data scraper all wait for a yes.

The request reaches people where they are, through a sound alert when an agent is waiting, an email with allow and decline links for agents started by email, and an API call that approves or rejects an action. A credit circuit breaker also pauses an agent at 600 credits on one message and asks whether to continue. Spaces and Groups decide beforehand which data, tools and systems an agent can reach.

Sourcedocs.dust.tt changelog (tool stakes and approval entries, January to October 2026) and API reference, validate an actionread 2026-10-21

Agentic workflows carry a user activity node, an interactive step where the workflow waits for a person to provide or receive information, either one field at a time in conversation or through a form that collects several fields at once, with node owners, input and output schemas, and fields that select approvers from a user list. Workflows pause for human validation, capture context and resume automatically, with traceability ready for audit.

Sourcedeveloper.watson-orchestrate.ibm.com/tools/flows/user_activities_node.mdread 2026-09-17

Business and Enterprise both carry SOC 2 Type II, GDPR compliance is stated throughout, and HIPAA can be enabled. A Trust Center sits at trust.dust.com, with a vulnerability disclosure page at dust.tt/home/vulnerability. Business includes SSO with Okta, Entra ID and JumpCloud for 5 or more seats, on demand. Enterprise adds SCIM provisioning, audit logs and advanced security controls, plus custom data retention and a custom MSA and DPA, so Business customers have SSO and Spaces but no provisioning or activity trail.

On both plans, data is organized into Spaces with configurable access controls, so admins decide which teams can reach which data sources. Integrations with Notion, Slack and Google Drive belong to Spaces, and Groups set permissions. Data is encrypted with AES-256 at rest and TLS 1.2+ in transit. Prompts, documents and outputs are never used to train models, though third party model providers may keep data for up to 30 days for safety and abuse monitoring before deleting it.

Sourcedust.tt/home/pricing feature table, /blog/what-is-data-sovereignty, /blog/secure-enterprise-software-ai-powered-teams and docs.dust.tt admin guideread 2026-09-12

Security and access control is named as a feature from the entry plan, and the Premium plan adds data isolation, a dedicated data space, end-to-end protection and a HIPAA-ready option. IBM does not say which identity providers and provisioning standards are supported, or whether access control reaches users, teams, tools, knowledge sources and model usage, and it publishes no certification or audit report scoped to the product.

Sourceibm.com/products/watsonx-orchestrate/pricingread 2026-09-17

On Enterprise, audit logs record what agents do as well as what people do. Each agent run, each tool an agent executes and each trigger that starts a run is its own event, and a tool event names the tool, the MCP server and the data sources it reached, and says whether the AI drove the action or a person started it.

The log is time ordered and tamper evident, searchable and exportable as CSV, and it streams to Datadog, Splunk, Amazon S3, Google Cloud Storage or any HTTPS endpoint. On every plan, analytics break credit use down by agent, member, model, tool and Pod, and a per call export lists each model call and tool call behind the bill.

Sourcedocs.dust.tt Audit Logs, Audit Logs events reference, Analytics and the consumption export APIread 2026-10-21

Traces visualize the complete path a request takes through an agent, with each observation recording a distinct unit of work, and they are reachable four ways: the orchestrate observability traces CLI command, the ADK Python library, the product interface and the API.

Sourcedeveloper.watson-orchestrate.ibm.com/traces/overview.mdread 2026-09-17

Customers on Business and Enterprise choose US or EU data residency, so a self serve customer at €24 a seat gets the choice. Enterprise adds single tenant deployment. The platform's code is public at github.com/dust-tt/dust, linked from the site footer, and Dust mentions self hosting without documenting how to do it. On EU hosting, data is stored on servers in the European Union, and model inference is routed to EU regions where available, which means not for every model, with Mistral named as the European provider.

Dust separates sovereignty, residency and localization, and notes that a European data center run by a US based company can still be compelled to hand data to American authorities. Dust is based in Paris, so that CLOUD Act argument works in its favor, and it says so. Ardabelle, a named customer, chose Dust on EU hosting and GDPR grounds for private equity deal documents. The specific EU region is not named.

Sourcedust.tt/blog/what-is-data-sovereignty and /home/pricing feature tableread 2026-09-12

The product runs as a fully managed service on IBM Cloud or on AWS, or in the customer's own on premises environment, and the ADK supports on premises setups and air gapped environments.

Sourceibm.com/products/watsonx-orchestrate/pricingread 2026-09-17

Ready agents and a template library come with every workspace. The default agents run as they are and each does its own job: @dust answers from all the company data a user can reach, @deep-dive spends ten to thirty minutes researching across the knowledge base, data warehouses and the web, and @analyst answers questions about how the workspace uses Dust.

Admins can switch each one on or off. Templates cover common use cases, and choosing one opens Sidekick with the template loaded, which drafts the instructions and suggests tools and data for the team to adjust before publishing. The workspace gallery then fills with the agents a company's own builders make.

Sourcedocs.dust.tt Templates and default agents pages (@dust, @deep-dive, @analyst)read 2026-10-21

An agents and tools catalog is a named feature of every plan, with ready-to-use domain agents added at the Standard plan, and the product API exposes catalog management operations for listing the applications and skills available from it. Partner built agents are sold beside it as separately metered add ons, among them a web research agent, a sales intelligence agent, a messaging agent and a document question answering agent.

Sourceibm.com/products/watsonx-orchestrate/pricingread 2026-09-17

Every plan includes more than 20 frontier models from OpenAI, Anthropic, Google, Mistral and DeepSeek, across the GPT, Claude, Gemini, Mistral and DeepSeek families, open source models among them. The customer chooses the model for each agent. No model is locked behind a higher plan, though more capable models may use more credits per message. Teams can pick the right model for each workflow and switch as their needs change.

Mistral AI, a French founded company, is the European option, and for work that must stay under European jurisdiction Dust offers EU hosted infrastructure with model inference in EU regions. Dust presents model choice as a way to avoid vendor lock in and geopolitical risk by controlling where data is processed and which providers are used, and calls being model agnostic a core feature. Usage analytics by agent and by model show what each model costs per workflow. Dust's MCP connectors and its Conversation and Data Source APIs are separate from model routing.

Sourcedust.tt/home/pricing model list and FAQ, /home/product, and /blog/what-is-data-sovereigntyread 2026-09-12

Models from multiple providers are imported as virtual models and assigned to an individual agent, and model policies coordinate several of them with a load-balance, fallback or single strategy, weights per target, and retry on named HTTP status codes; a policy is assigned to an agent the same way a single model is. On the product side, the same surface is an AI Gateway for integrating models from several providers with configurable routing policies. Model policies are in public preview, while assigning a model to each agent is not in preview.

Sourcedeveloper.watson-orchestrate.ibm.com/llm/model_policies.mdread 2026-09-17

The platform has its own API. Business includes a Conversation API for driving conversations with agents from outside, and Enterprise adds a Data Source API that writes into the knowledge layer. Platform documentation at docs.dust.tt, linked from the site footer, offers an llms.txt index of every page in Markdown, with endpoints in OpenAPI.

The platform's code is public at github.com/dust-tt/dust, and a developer platform at dust.tt/home/solutions/dust-platform covers Dust Apps, described as an extensible, API first platform for custom integration and LLM orchestration. Programmatic use is metered at $0.01 per credit on Business and custom on Enterprise. Zapier, Make, n8n and Power Automate are available on both plans, and a Chrome extension brings agents into other tools. The MCP connectors run the other way, letting Dust call other systems' tools. No endpoint reference or SDK page is cited, and the OpenAPI specification is mentioned but not shown.

Sourcedust.tt/home/pricing developer tools table, docs.dust.tt welcome page and site footerread 2026-09-12

IBM publishes an Agent Development Kit with a Python SDK and an orchestrate command line (agents import, evaluations, observability traces, models policy), a machine readable documentation index, and an OpenAPI specification for the server API with reference pages for each operation on agents, flows, connections, catalog management, evaluation and monitoring.

Sourcedeveloper.watson-orchestrate.ibm.com/llms.txtread 2026-09-17

A builder can try a change before it goes live. A preview area beside the agent builder runs the draft agent on real questions, and the docs advise testing changes there until the answers are consistent.

Teams that manage agents as code can keep agent and skill definitions in YAML in a GitHub repository with the official GitHub Action, review edits in pull requests and promote them from a development workspace through staging to production, and changes Sidekick proposes from a conversation arrive as cards to accept or decline. Thumbs up and down on each answer are collected and readable through the API.

None of this scores a change, since there are no test cases, pass rates, evaluators or comparisons between two versions of an agent, so judging a change still rests on someone reading the answers.

Sourcedocs.dust.tt Troubleshooting your agent, the dust-github-action changelog entry and the feedback APIread 2026-10-21

The ADK ships an evaluation framework that assesses agent behavior by simulating user interactions and comparing the resulting trajectories step by step against reference data the customer generates, records or writes by hand, logging every deviation from the expected path and returning a metrics summary saved as CSV. The cycle before deployment is develop, evaluate, analyze, improve, with an analyze command for reading results and a rubric, and evaluations run against the local Developer Edition and against draft environments of SaaS and on premises instances.

Sourcedeveloper.watson-orchestrate.ibm.com/evaluate/overview.mdread 2026-09-17

Pods and Frames run on a shared virtual computer and automations, a shared environment where agents run code and produce artifacts, not one where an agent operates a graphical interface. Credits are charged for tools such as search, data retrieval, code execution and actions in connected apps, and interface control is not among them. The Chrome extension lets a person reach Dust agents while browsing, and no agent drives the browser.

Every path in and out of Dust is a maintained connector, an MCP server or an API, so a third party redesigning its interface does not affect it, and Dust maintains typed connectors instead of scraping. There is no hosted or local browser session, desktop or remote computer control, RPA, recorder or extension that acts on a page for the agent. Dust does not explain what its shared virtual computer can and cannot do.

Sourcedust.tt/home/product, /home/pricing credits FAQ and /home/chrome-extensionread 2026-09-12

Agents act through tools that call APIs and services, connections to enterprise systems, MCP and the channels a buyer configures. IBM does not describe browser, desktop or remote computer control.

Sourceibm.com/products/watsonx-orchestrate/pricingread 2026-09-17