BRIEFING DECK

How an agent is kept to its rules

A four-slide briefing: why what a user asks can be manipulated but what your systems know cannot, how a written rule keeps an agent's actions in check, and the shortcut route an agent will find if nobody looks.

SLIDE 1 OF 4
HOW THE RAIL IS WIRED

Intent can be talked into anything. Context cannot. Actions need a policeman.

Three things are in play. They are not the same kind of thing.

IntentWhat was askedManipulableContextWhat your systems knowDeterministicThe gateReads bothA written ruleActionBooks, or refusesNothing else

Every hole has the same shape. A reachable intent, in front of an ungated action.

The rulebook is a file. The model never edits it1 / 4

Try it yourself

Everything in this deck is available through one API. Read the reference, then try a call with a test key.

Try our API

What you get

Send us your guardrail policies and tool definitions. You get back every route to a forbidden action, each with the conversation that triggers it and a fix that has already been checked.

Explore the productsRegister Interest