Silver
Arcade
About Arcade
Arcade is the action runtime for enterprise agents. We enforce security and governance policies on every action, execute reliably across every system, and govern agents from a single control plane. Configure once and use any model, framework, and client. Deploy the first agent the same way you deploy the hundredth.
Product types
- Compliance and Regulation Tools Services
- Productivity Tools
- Core AI Infrastructure
- Security
Sessions at Ai4 2026
Build Agents Your Security Team Will Approve: Skills, Loop Engineering, & Governance with Arcade.dev [RSVP REQ'D]
This event requires an RSVP; to attend, submit form here
Coding agents are confined to the terminal because they lack authenticated access to real systems. This workshop demonstrates how to bridge that gap using Arcade.dev.
We start with an isolated agent, then introduce the Arcade MCP gateway to provide tools with live per-user OAuth, transforming workflows into reusable Agent Skills.
We then explore loop engineering: removing the human while maintaining control. We showcase how an email can trigger an unattended agent that reproduces bugs and ships fixes with human-in-the-loop checkpoints enforced at the infrastructure layer.
By vaulting and scoping credentials per user, background agents move beyond demos into production-ready reasoning and action layers, providing the audit trails enterprise security teams require.
Coding agents are confined to the terminal because they lack authenticated access to real systems. This workshop demonstrates how to bridge that gap using Arcade.dev.
We start with an isolated agent, then introduce the Arcade MCP gateway to provide tools with live per-user OAuth, transforming workflows into reusable Agent Skills.
We then explore loop engineering: removing the human while maintaining control. We showcase how an email can trigger an unattended agent that reproduces bugs and ships fixes with human-in-the-loop checkpoints enforced at the infrastructure layer.
By vaulting and scoping credentials per user, background agents move beyond demos into production-ready reasoning and action layers, providing the audit trails enterprise security teams require.
