Integration
Connect Beanstalk to Relevance AI
When something happens in Beanstalk, your agent does the next thing in Relevance AI. Describe it in plain language and the automation is built, tested on every branch and kept running.
Build it
What do you want Beanstalk and Relevance AI to do together?
Describe it and your agent reads both APIs, builds the automation, tests every branch and ships it. The list below is what exists today, not the limit.
Ask the assistant
You'll sign in before anything runs. What you typed comes with you.
Or work from Claude Code
Install the APIANT plugin for Claude Code and build, edit, test and read run history from your terminal. Every plan gets this, including free, and it spends no assistant credits.
Connect Claude CodeEverything your agent can do with Beanstalk and Relevance AI
Triggers and actions 2 triggers ยท 12 actions
Trigger
New RepositoryPolls for newly created repositories.
- New User
Polls for newly added users.
- Add public key
Add an SSH public key for Git authentication. POST /api/public_keys.json with name, content (single public SSH key).
- Create Repository
Create a new repository in the Beanstalk account.
- Get Repository
Retrieve a single repository by ID.
- Get User
Retrieve a single user by ID.
- List public keys
List SSH public keys for users on the account. GET /api/public_keys.json (optional user_id for admins).
- List Repositories
List all repositories in the Beanstalk account.
- List Users
List all users in the Beanstalk account.
Action
Get TaskGet a single task (conversation thread) by ID for an agent, including status and messages. Endpoint hint: Agent.getTask / task status polling.
- List Tasks
List tasks (conversation threads) for an agent, paginated/sortable/filterable by status. Endpoint hint: Agent.getTasks.
- Message Agent
Sends a message to an Agent. Doesn't wait for a response.
- Message Workforce
Sends a message to a Workforce. Doesn't wait for a response.
- Run Tool
Execute a Tool in Relevance AI. Waits for a response for up to 60 seconds.
No trigger or action matches that. Ask your agent to add it: it reads the API documentation and builds what you describe.
Each app on its own
Reviews