11 available actions
What your AI agent can do in VLM Run
VLM Run provides multimodal agents, structured extraction, predictions, files, skills, feedback, and evaluation APIs. This page lists every available action. Your agent only receives the actions and permissions required for the role you approve.
Showing all 11 actions.
Common starting points
- Find SkillsList VLM Run skills or find one exact skill by ID, name, and optional version.
- Get RunGet the current status and result of one structured-extraction prediction or agent execution; call repeatedly to poll asynchronous work.
- Create SkillCreate a reusable skill from exactly one uploaded zip, prompt, or chat session.
- Upload FileUpload a local file to VLM Run for extraction, agent input, or skill creation.
- Execute AgentStart a VLM Run agent execution from an existing agent name or inline configuration over multimodal inputs.
- Extract Structured JSONStart structured JSON extraction from images, a document, a video, or audio using a domain, custom schema, or skill.
Browse all 11 actions by capability
Open a capability to see every supported action and its description.
Find & reviewLook up and review existing recordsView 6 actions
- Find FilesList uploaded files or find one by file ID or MD5 hash.
- Find SkillsList VLM Run skills or find one exact skill by ID, name, and optional version.
- Get RunGet the current status and result of one structured-extraction prediction or agent execution; call repeatedly to poll asynchronous work.
- List AgentsReturn agents available to the connected account for selection before execution.
- List ArtifactsList artifact metadata belonging to exactly one chat session or agent execution.
- List RunsList structured-extraction predictions or agent executions for the connected account.
Create & communicateCreate records or send supported messagesView 2 actions
- Create SkillCreate a reusable skill from exactly one uploaded zip, prompt, or chat session.
- Upload FileUpload a local file to VLM Run for extraction, agent input, or skill creation.
Update & manageChange and manage existing recordsView 1 action
- Execute AgentStart a VLM Run agent execution from an existing agent name or inline configuration over multimodal inputs.
Other actionsSpecialist and administrative actions.View 2 actions
- Discover Extraction SchemasList supported structured-extraction domains, or return the full JSON schema for one domain when domain is provided.
- Extract Structured JSONStart structured JSON extraction from images, a document, a video, or audio using a domain, custom schema, or skill.
Connection record
A connection you can control.
- Sign-in
- Customer-managed key
- Setup
- Use a key you create and control. It is stored securely and limited to the work agreed for the role.
- Boundaries
- Only the approved role and actions.
- Off switch
- Revoke the connection from your account.
FAQ
Before you connect VLM Run
How does the agent connect to VLM Run?
With a key you create and control. It is stored securely, permissions are limited to what the agent needs, and you can revoke it at any time.
What can the agent actually do in VLM Run?
The page above lists the 11 actions currently available through the VLM Run connection. The role determines which of those actions the agent may use, and write access is only enabled when the workflow needs it.
Is VLM Run included in my plan?
Connections are priced per tool on top of the base plan. Some are included and some are premium. See pricing for how connection charges work.
How long until VLM Run is ready?
Timing depends on the sign-in method, permissions and workflow being connected. We confirm the scope and setup plan before enabling the connection.
Bring the workflow together
Ready to put VLM Run to work?
Start with the responsibility you want off your plate. We’ll map the connection and the boundaries around it.