Accelerate recruiting and hiring
Organize candidate information, prepare job descriptions, and support recruiting workflows.
A workspace where non-engineers build and run custom AI agents connected to Slack, Notion, GitHub, and other everyday tools.
Dust is a workspace for building and running custom AI agents. Users create agents with defined skills, knowledge, and tools, set up multi-agent workflows that run on a schedule or in response to an event, and build simple interactive dashboards called Frames. It is aimed at what Dust calls 'AI Operators,' people inside a company who manage agents for their team without relying only on engineers. It connects to more than 20 frontier models, including those from OpenAI, Anthropic, and Google, and to over 20 data sources such as Slack, Notion, GitHub, Google Drive, and Zapier, with Model Context Protocol support for custom connections. Dust holds SOC 2 Type II certification and supports single sign-on through Okta, Microsoft Entra ID, or JumpCloud, plus SCIM provisioning.
This fits a company that wants a few non-engineering staff to build and maintain their own agents day to day, using tools it already relies on like Slack and Notion, instead of routing every request through IT. A pilot with a Pro plan for one or two teams, such as customer support or marketing, is a reasonable way to test agent quality before a wider rollout. Published pricing lists a free tier with a one-time 500 credits, a Pro plan near 24 euros a month per seat billed yearly with 8,000 monthly credits, a Max plan near 120 euros a month with 40,000 credits, and custom Enterprise pricing above that; treat these as planning numbers in euros. Watch credit usage closely, since heavy agent use can burn through a plan's monthly allowance faster than expected.
Potential matches to review against your requirements. Explore matching tools or read a task guide before you choose.
Organize candidate information, prepare job descriptions, and support recruiting workflows.
Summarize information, compare files, and identify key findings.
Turn approved content and customer requirements into proposal drafts for your sales team.
Find answers across your documents and internal resources.
Bring key business metrics together in dashboards and summaries for leadership.
Use historical trends and business data to plan for future customer demand.
Plan production around orders, available capacity, materials, and delivery deadlines.
Identify bottlenecks and support frontline teams with clearer work instructions and operational insights.
Balance stock availability with demand to reduce shortages and excess inventory.
Use equipment data to spot potential issues and plan maintenance before breakdowns.
Find relevant answers, route requests, and help service teams respond to customers sooner.
Analyze spending, compare suppliers, and identify opportunities to improve purchasing.
Explore external sources to support business decisions.
The industries and leadership roles this tool is most often matched with.
How one company factor at a time moves the modeled score. The published score is unchanged.
These estimates cover licensing, setup, integrations, staff time, security, administration, and support.
| Cost measure | Low | Base | High |
|---|---|---|---|
| First-year total | $57.8K | $91.9K | $149.2K |
| Three-year total | $121.4K | $184.7K | $288K |
| First-year cost per unit | $57.8K | $91.9K | $149.2K |
| Average annual cost per unit (over three years) | $40.5K | $61.6K | $96K |
| Component | Low | Base | High |
|---|---|---|---|
| Licensing and usage | $16.5K | $22K | $29.7K |
| Implementation | $9.6K | $16K | $27.2K |
| Integration | $12.1K | $22K | $39.6K |
| Staff time and change management | $6.3K | $9K | $12.6K |
| Security | $4.9K | $7K | $10.5K |
| Administration | $3.8K | $5K | $6.8K |
| Support | $1.9K | $2.5K | $3.4K |
Estimate assumptions: This scenario uses a category-based allowance, not a verified price for this product. Based on 1 production deployment. Confirm the vendor’s billing unit and current price or quote before budgeting.
Benefits have not been estimated: The current research does not estimate potential savings, return on investment, or how long it would take to recover the cost. Earlier benefit estimates are excluded.
Confirm current product identity, commercial packaging, data processing terms, sign-in and access rules, retention, integrations, support model, implementation effort, and rollback conditions.
Verify identity, package, availability, ownership, pricing, and security evidence before approving a pilot
Do not approve a pilot yet. Verify the current product identity, package, availability, owner, pricing, and security evidence; then define one workflow, a baseline, and rollback criteria.
Define what success looks like for a test of Dust and assign someone to lead it.
Once the requirements above are met, compare a small trial with how your team works today.
Track adoption, output quality, business results, and actual costs against the estimate.
Use the results to decide whether to stop, adjust, or expand the pilot.
Confirm encryption, how the vendor uses your data, customer data separation, how long data stays and how to delete it, activity records, sign-in and user setup, where data is handled, other companies that process data, past incidents, and what your team must manage.
Export Dust agents, instructions, knowledge scopes, tools, evaluations, schedules, usage, and audit history. Recreate managed connectors and memory on the replacement, and retain authoritative content outside the workspace so agent retirement does not remove the business record.
Do not approve a pilot yet. Verify the current product identity, package, availability, owner, pricing, and security evidence; then define one workflow, a baseline, and rollback criteria.
A free, open-source developer library from OpenAI for building custom AI agents in code, with tools and handoffs between agents.
Why it’s an alternative—
Compare with OpenAI Agents SDKlangchain.com
A free, open-source developer library for building multi-step AI agent workflows with fine control over each step.
Why it’s an alternative—
Compare with LangGraphA platform for building teams of AI agents that handle sales, support, and operations tasks, marketed as an 'AI workforce.'
Why it’s an alternative—
Compare with Relevance AIAn open-source developer framework for organizing several AI agents into a team with defined roles, plus a paid governance layer.
Why it’s an alternative—
Compare with CrewAIWhere to check the product, price, security, and support.
Research observations recorded: 1. Evidence quality: Good support.
Recorded score and category rank across research updates.
Answer a few questions about your company and compare this tool with others. The research score above stays the same.
Want help moving from research to action? Explore TriVista’s AI consulting services →