Stacks/Enterprise agent platform
Dust's Temporal-backed agent platform
Dust runs its agent platform on Temporal Cloud at more than 10 million activities a day, with PostgreSQL, GCS, Kubernetes, and Datadog around it. Connectors turn Slack, Notion, GitHub, and similar events into durable workflows for ingestion, enrichment, and agent actions. CTO Stan Polu's account, published by Temporal, emphasizes retries, long-running work, and horizontal scale without a custom orchestration layer.
- Use case
- A horizontal enterprise agent platform whose agents live in a company's existing tools — Slack, Notion, GitHub, Confluence, Salesforce, and more — and run real workflows such as commenting on pull requests from a design doc, filing a Slack bug as a ticket, and a Tracker product that proposes updates to stale documents and even to agents' own prompts
- Category
- Enterprise agent platform
- Team size
- not stated
- Orchestrator / framework
- From the beginning, Dust has used Temporal as the orchestration engine. Events in connected tools trigger Temporal workflows that pull data, transform it, run AI processing, update indexes, or take follow-up actions; some workflows last seconds and others hours. Dust runs over 10 million Temporal activities per day on Temporal Cloud and scales by running more workers.
- Memory
- Company data is ingested, chunked, embedded, and indexed so agents have workspace context. The rest of the system is built on PostgreSQL, GCS, and Kubernetes.
- Evals
- not stated
- Observability
- Temporal's workflow visibility is used for inspection and recovery. Workflows are also 'deeply instrumented with Datadog,' giving engineers visibility into retries, errors, and completion events.
- Monthly cost
- not stated
- Models
- not stated
- Other tools
- PostgreSQLGoogle Cloud StorageKubernetesSlackNotionGitHubConfluenceSalesforce
- Source
- https://temporal.io/blog/how-dust-builds-agentic-ai-temporal
Stan Polu (Dust co-founder and CTO), as told in a Temporal blog post by Clair Byrd · May 28, 2025
Related
More like this
SRE / incident response
Date not stated
Traversal AI SRE investigation agent
Autonomous production-incident investigation: agents reason over a live 'Production World Model' of a customer's systems, narrow candidate signals, and produce a root-cause report while someone is watching an outage
Internal engineering platform
Aug 3, 2026
Duolingo's production agent platform
An internal platform so any Duolingo team can define a production agent once and invoke it from Slack, internal sites, a CLI, or another Temporal workflow. In use for fixing CI failures, addressing code-review comments, and a Slack bot for release managers that investigates crashes and summarizes findings
Fintech / internal platform
2026
Block KGoose (Money Bot, Manager Bot, and G2)
A shared AI agent platform at Block that powers Money Bot (a Cash App financial assistant for peer-to-peer payments), Manager Bot (a Square merchant assistant), and G2 (an internal productivity platform)