Arcade.dev | The Actions Runtime

@TryArcade

Ship agents. Not auth infrastructure. | github.com/ArcadeAI

San Francisco, CA

arcade.dev

Replies Reposts Media Articles

Arcade.dev | The Actions Runtime
@TryArcade
Sep 3
The worst ROI on an agent: a large token bill for work that never got finished. Paying a painter who does a great job is not a problem. Paying for a bad job, or never letting them in the house because you can't be sure what they'll touch, is. The question isn't just what you're
1
Arcade.dev | The Actions Runtime
@TryArcade
Sep 3
If you've run an agent on anything long, you know this one. You send it off on a two hour job, come back, and it stopped ten minutes in waiting for you to authorize. Arcade now clears all of it up front. The agent maps out what it needs and you approve it all in one pass before
00:00
2
Arcade.dev | The Actions Runtime
@TryArcade
Sep 2
Can this agent, on behalf of this user, take this action, on this resource, right now? AI agent governance is the ability to answer that at every tool call, before the action goes through. We’ve covered why agents need their own governance and why guardrails won’t do it. This
1
Arcade.dev | The Actions Runtime
@TryArcade
Sep 1
Most teams building agents start with guardrails, which is the right instinct but also only half the job. A guardrail lives inside the model and the agent, the one part of your stack that can be talked past. Replit's agent deleted a production database during a code freeze with
3
Arcade.dev | The Actions Runtime
@TryArcade
Aug 31
With people, the actor and the accountable party are the same. The analyst who runs the report answers for it, which is why “is this user allowed?” has been enough. With agents, that framework comes apart. The agent acts, a human carries the consequence, and the controls you