Lays out layered defenses against prompt injectionAn attack that hides instructions in content an AI will read — a webpage, email, or document — tricking it into following the attacker instead of the user.Full definition → and misread intent in agents, spanning model, agent harnessThe scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.Full definition →, tools and environment. It gives builders a checklist for where to put controls.
Terms in this piece · Glossary
alignment — The work of making AI systems actually pursue what their builders and users intend, rather than something subtly or dangerously different.
agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
prompt injection — An attack that hides instructions in content an AI will read — a webpage, email, or document — tricking it into following the attacker instead of the user.
