Dust AI Review 2026: Team Agents, Pricing, Security, and Fit
A research-based Dust review covering capabilities, pricing, privacy, limitations, and a fair buyer test.
Bottom line
Dust gives teams flexible models, connectors, agents, and governance, but credit consumption, connector scope, permissions, retrieval quality, and enterprise plan boundaries need a real workload test.
The decision
Should you choose Dust?
Dust is worth testing for teams that want employees to build and operate shared AI agents over company knowledge and tools while retaining model choice and administrative controls. Its flexibility also creates the buying risk: every connector, agent instruction, tool permission, model, and credit-consuming action needs an owner. The relevant metric is accepted work per credit after review—not agents deployed.
Best for
Teams building shared agents over internal knowledge and tools; Organizations that value model choice and US or EU residency.
Choose something else if
Teams seeking a fixed-price unlimited assistant; High-consequence write actions without approval and rollback
Evidence
Verified research · rating withheld
Pricing checked
From $24 · 2026-09-29
Free access is available, with limits.
Yes. The free business tier includes 500 lifetime credits and is best treated as a bounded evaluation allowance.
In this guide
Short answer
Dust is worth evaluating for cross-functional teams that want shared AI agents connected to company knowledge and tools while retaining model choice and governance. Its self-serve Pro tier gives smaller teams a credible starting point. The decisive issue is not how many agents you can build; it is whether permissions, retrieval, actions, audit logs, human review, and credit economics remain predictable on real work.
Best for
- Cross-functional teams building shared agents
- Companies needing model flexibility
- Teams prepared to govern connectors and permissions
Look elsewhere if
- Unbounded autonomous actions
- Buyers unable to forecast usage credits
- Sensitive deployments without security review
What Dust verifiably does
Dust documents custom and global agents, shared workspaces, reusable skills, schedules and triggers, more than 70 connectors, more than 20 frontier and open-source models, MCP, collaboration, permissions, analytics, and enterprise deployment options. Agents can retrieve company context and use tools for search, analysis, code execution, and actions in connected applications.
Important limitations
Credits are workload-dependent, so seat price alone does not predict total cost. Connecting Slack, Drive, GitHub, Salesforce, Zendesk, or other systems expands the accessible data surface and may sync more than a user expects. Retrieval can miss or mis-rank sources, agents can take incorrect actions, and retention, audit logs, SCIM, single tenancy, and some residency controls are enterprise features.
Pricing snapshot
Free includes 500 lifetime credits. Pro is $24 per seat/month with 8,000 credits per seat; Max is $120 with 40,000 credits per seat. Enterprise uses pooled credits, volume pricing, and custom terms. Credit use varies by model, task complexity, retrieval, code execution, search, and connected actions. Reviewed August 24, 2026.
A fair buyer test
Give one cross-functional team two bounded agents: a read-only account brief and an approval-gated CRM hygiene workflow. Seed conflicting sources, revoked access, private records, and tool failures. Measure accepted answers, citation quality, blocked access, incorrect actions, escalations, latency, per-task credits, audit detail, and maintenance.
Final verdict
Dust earns a shortlist for teams that need collaborative agents, broad connectors, and model flexibility with a self-serve entry point. It is less attractive when workloads are hard to bound or the buyer cannot rigorously map connector scope, permissions, retention, and credit use.
This is a research-based assessment, not a claim of hands-on product testing. Product, pricing, privacy, security, and usage claims were checked against the first-party sources below on August 24, 2026. Verify current terms and run the proposed test with approved data before adoption.
Transparency
How this guide was checked
Editorial accountability
Who checked this guide
- Evaluation type
- Hands-on evaluation
- Last materially checked
- Evidence
- 5 listed sources
Hands-on testing is identified explicitly. Research-based coverage uses cited product documentation and other named sources; it does not imply every paid plan was used. Read the full methodology.
Editorial freshness
Pricing and material product claims were checked September 29, 2026.
Review evidence
What this guidance is based on
- Editorial basis
- Current first-party product, pricing, help, security, privacy, and terms documentation
- Review type
- Research-based product assessment
- Material review date
- August 24, 2026
- Buyer test
- Controlled workflow test with output, correction, cost, permission, and ownership checks
Important limits
- • DiscoverAI did not complete the proposed long-term paid deployment for this research-based review.
- • Features, prices, limits, security controls, privacy terms, and usage rights can change; verify the linked first-party pages before purchase.
Standardized benchmark coverage
How this review maps to the research benchmark
Citation accuracy
Eligible · not yet runThis review describes source-grounded research, retrieval, or document work. A controlled product run is required before scoring.
Read protocol v2026.10-v1 →Thematic analysis
Not applicableThe reviewed workflow is not qualitative evidence analysis, so a thematic-analysis score would be misleading.
Read protocol v2026.10-v1 →Eligibility is not a product score. DiscoverAI publishes results only after output collection, blinded adjudication, reproducibility checks, and severe-error review.
Open the optional evaluation worksheet
Reusable trial worksheet
Test Dust before you commit
Turn this review’s buyer test into evidence. Your entries autosave only in this browser and are never added to shared shortlist links.
Confirm the tool meets every must-have workflow and stakeholder requirement.
Review starting point: Teams building shared agents over internal knowledge and tools; Organizations that value model choice and US or EU residency; AI operators prepared to own permissions, evaluations, and credit budgets
Run the same representative work you would use in production; do not score a polished demo.
Review starting point: Give one cross-functional team two bounded agents: a read-only account brief and an approval-gated CRM hygiene workflow. Seed conflicting sources, revoked access, private records, and tool failures. Measure accepted answers, citation quality, blocked access, incorrect actions, escalations, latency, per-task credits, audit detail, and maintenance.
Calculate the effective cost per accepted result, including usage, review, corrections, and required add-ons.
Review starting point: Dust lists a free tier with 500 lifetime credits, Pro at €24 per seat per month billed yearly with 8,000 monthly credits, and Max at €120 with 40,000 credits. Credits reset rather than roll over. Model choice, research, retrieval, code, tool use, and multi-step orchestration consume different amounts; programmatic use is listed at $0.01 per credit.…
Define an acceptance threshold, test known answers and edge cases, and record every correction.
Review starting point: Editorial quality signals: features 0.0/5. Validate these signals in your own work.
Verify what data enters the product, who can access it, how long it is retained, and whether it trains models.
Review starting point: Use approved low-risk data first. Check roles, consent, deletion, subprocessors, model-training settings, and the contract—not only the marketing page.
Test the real handoffs, permissions, failure states, and export path your team depends on.
Review starting point: Slack, Notion, Google Drive, GitHub, Microsoft 365, MCP
Record training, governance, reliability, accessibility, ownership, and change-management risks before rollout.
Review starting point: Teams seeking a fixed-price unlimited assistant; High-consequence write actions without approval and rollback; Organizations without owners for connected knowledge and agent behavior
Loading saved worksheet… · private to this device or your optional account
Community evidence
How verified users put Dust to work
Structured, editor-moderated experience—not star ratings. This complements our independent review and never changes its score.
No approved community evidence yet. Be the first verified user to contribute.
Sources and verification
Product details and claims were checked against the following primary sources.
Frequently asked questions
Is Dust AI free?
Yes. Dust lists a Free tier with 500 lifetime credits, intended for limited evaluation.
How much does Dust cost?
Pro is currently $24 per seat/month and Max is $120; Enterprise is custom. Usage credits vary by model and task.
What can Dust agents connect to?
Dust advertises more than 70 connectors, including Slack, Notion, Drive, GitHub, Salesforce, and Zendesk, plus MCP options.
Does Dust use customer data for model training?
Dust says customer data is not used for model training. Buyers should still verify model-provider, retention, connector, and enterprise contract terms.
Recommended tool
Use Dust if this workflow fits your team
Dust is worth testing for teams that want employees to build and operate shared AI agents over company knowledge and tools while retaining model choice and administrative controls. Its flexibility also creates the buying risk: every connector, agent instruction, tool permission, model, and credit-consuming action needs an owner. The relevant metric is accepted work per credit after review—not agents deployed.
Tools mentioned in this article
Dust
Dust is worth testing for teams that want employees to build and operate shared AI agents over company knowledge and tools while retaining model choice and administrative controls
Dust is worth testing for teams that want employees to build and operate shared AI agents over company knowledge and tools while retaining model choice and administrative controls. Its flexibility also creates the buying risk: every connector, agent instruction, tool permission, model, and credit-consuming action needs an owner. The relevant metric is accepted work per credit after review—not agents deployed.
Cassidy AI
A no-code platform for company-grounded AI agents and production business workflows
Cassidy combines knowledge, agents, workflows, approvals, and integrations, but opaque paid pricing, credit economics, source freshness, permissions, and exception handling determine production value.
Relevance AI
A no-code platform for building AI agents, tools, and coordinated workforces
Relevance AI can make agent orchestration accessible, but action limits, model credits, permissions, evaluation, retention, and human escalation determine production readiness.
Glean
A practical AI tool for enterprise search workflows
Glean helps professionals improve enterprise search workflows with AI-assisted drafting, automation, analysis, or production features.
Read next
