Durable runs
Built on our durable workflow engine. Runs survive crashes and deploys, retry cleanly and never silently stop.
Foundry Workflows
Build an agentic workflow on your own machine, as a Claude Code project or any script. Add one small file, studio.yaml, and deploy it. Foundry runs it on a schedule, on a webhook or by hand, and asks a person before anything that matters.
curl -fsSL https://app.foundrystudio.dev/install.sh | sh
Then run studio login.
One workflow, start to finish
The receipts workflow from the demo. Your agent does the work, your code does the matching, and a person approves anything that goes to a supplier.
Today all three kinds work inside one run of your agent. Workflows built from separate agent, code and person steps, with agentic steps you can switch off, are on the way.
How it works
You build with the tools you already use. Foundry does the part that never ends: running it every day, and telling you when something needs you.
Work in Claude Code as you do now: CLAUDE.md, skills, subagents, slash commands, MCP servers and its permission settings. Or write any script, such as one on the Claude Agent SDK. Add studio.yaml.
studio workflows dev runs it on your machine with the same runner the cloud uses, against your real connections.
studio workflows deploy, or ask Claude Code to deploy it: our Claude Code plugin knows how. It tells you when it runs next and which connections or secrets it still needs.
On a schedule, on a webhook or by hand. Each run's steps show in a Studio thread. If a run fails, you get a push.
One small file
studio.yaml says how it runs.Your code stays as it is. This file sits beside it and says what to run, when, and what it may touch.
version: 1
name: receipts
description: File receipts from the finance inbox to Drive
entry:
claude: "/file-receipts"
triggers:
- cron: "0 7 * * *"
tz: Europe/London
- webhook: {}
connections: [google.gmail, google.drive]
secrets: [XERO_TOKEN]
egress: [api.xero.com]
approvals:
ask: ["mcp__studio__gmail_send"]
limits: { timeout: 10m }
state: state/
entrytriggersconnectionssecretsstudio workflows secrets set; they are stored encrypted.egressapprovals.asklimitsstateRun it for good
Built on our durable workflow engine. Runs survive crashes and deploys, retry cleanly and never silently stop.
Each run's steps show in a Studio thread, so you can see what it did. If a run fails, a push tells you.
Every deploy is a new version. studio workflows rollback takes you back to an earlier one.
studio workflows logs shows what happened in each run. Pause a workflow and resume it when you are ready.
In charge and contained
approvals.ask waits for a person, such as sending an email or pushing codestudio workflows secrets set, stored encrypted and never written to filesOpen by design
The workflow lives in your own repository, built with your own tools.
studio.yaml is short and readable. Nothing proprietary goes into your code.
Bring your own model key. Anthropic is the default; use any model you like. Model usage is billed to you by your provider.
Your Claude Code project comes as it is: CLAUDE.md, skills, subagents, slash commands and MCP servers.
Pricing
Free
Need more?
Questions
No. Any script works, including one built on the Claude Agent SDK. A Claude Code project is one way to build a workflow, not the only one.
Any model. Anthropic is the default, through your own API key, and you can use any other provider or model with its own key. Model usage is billed to you by your provider.
In Google Cloud, in the London region (europe-west2). Each run gets its own container.
Yes. It is your repository and a plain YAML file, with nothing proprietary in your code. The runner that runs it is open source (Apache-2.0): foundry-workflow-runner runs the same studio.yaml on your own computer or in a container you build, with no Studio at all. Export to open standards is on the way.
No.
It retries what is safe to retry, then stops cleanly. You get a push, and the run's thread shows exactly what happened.
Free for 3 workflows. Bring your own model key.
Start free