Set trust boundaries around sensitive data, untrusted instructions, retrieved content, agent permissions, and consequential actions.
Tutorials
Follow these lessons in order, or jump directly to the topic you need.
Your RAG app is working beautifully. Users ask questions, your system retrieves the right documents, and the model produces clear, grounded answers. Then…
Read tutorial
A team ships an assistant that reads inbound email, searches a knowledge base, and can send replies. Then the argument starts. "We added a guardrail." "The…
Read tutorial
You can recite that untrusted content can carry instructions. Then someone shows you a proposed action and asks, "Should this run?" and the recitation…
Read tutorial
You're staring at a chat window. You've drafted a prompt that would save you an hour of work—if you paste in the real document. The cursor blinks. Your…
Read tutorial
The most common mistake I see when teams first put an LLM into a real workflow is also the most understandable one: they bolt a human approval step onto…
Read tutorial
The moment you give an agent a tool, you stop deciding what it does and start deciding what it is allowed to do. The real design question is not "can the…
Read tutorial
Two permission grants land on the review table. One lets the agent read every ticket and send email. The other lets it read assigned tickets and draft…
Read tutorial
A proposed tool call sits on your screen: send the summary to the client. You have a policy document open in another tab. Is this allowed, does it need…
Read tutorial
If you've spent any time reading about AI security, you've probably seen "jailbreak" and "prompt injection" used interchangeably. The terms blur because…
Read tutorial
You have a real document you want an LLM to help with—maybe a customer support ticket, a contract, or a set of notes. It's full of useful context. It's…
Read tutorial
A support chatbot answers a customer's question with total confidence. The answer cites a document from the company knowledge base. The only problem: the…
Read tutorial
Most people agree with data minimization right up until the moment the task needs context. Then the full customer email goes into the chat window, because…
Read tutorial
A review queue is a purchase order. You are buying a reduction in expected loss, and the only real question is whether the reduction is worth the price.
Read tutorial
A citation chip proves a chunk was retrieved. It does not prove the chunk was ever authorized or trustworthy.
Read tutorial
The output is sitting in front of you. It reads well. It answers the question. And you still cannot say whether it should ship.
Read tutorial
The cursor is blinking in the paste box. You have a real task, a real dataset, and no rule that clearly says yes or no. This article is a set of reps for…
Read tutorial
A team wants to prove that minimization is safer. So they multiply two numbers they invented, get a smaller product for the minimized option, and present…
Read tutorial