Checking LLM-generated data or actions against explicit structural, semantic, evidence, or application requirements before use.
Tagged articles
23 articles in this tag.
Here's the scene I've watched play out more times than I can count: someone builds their first agent, gives it a task, and watches it loop. It calls a…
Read tutorial
Reading about AI tools builds recognition, not skill. Skill comes from running the tool, inspecting the output, and making one small change to see what…
Read tutorial
A model returns clean JSON. The pipeline writes it to a table. One wrong field quietly poisons everything downstream.
Read tutorial
The first prompt is not a test of Claude. It is a test of whether you described the task.
Read tutorial
The model returns clean JSON. Every brace closes. Every key is present. And the answer is still wrong.
Read tutorial
An LLM can sound certain and still be wrong. The skill that matters is not deciding whether to trust the model wholesale—it is learning to sort each claim…
Read tutorial
That single distinction separates a demo from a system. When you chat with an LLM directly, you are the pipeline: you judge the output, check the facts,…
Read tutorial
Most developers don't fail with AI coding assistants because the code is wrong. They fail because the code looks right.
Read tutorial
An LLM that reads a document and returns JSON is not performing a database import. It is performing an act of reading—and reading, even by a very capable…
Read tutorial
An LLM can draft a working function in seconds. The harder truth is that the code it writes still needs to be tested, debugged, and understood before it…
Read tutorial
You asked the model for JSON. You defined the schema, listed the required fields, and specified the exact types. The response came back wrapped in markdown…
Read tutorial
A portfolio is not a trophy shelf. It is evidence of judgment — proof that you can pick a real problem, make the right tradeoffs, and ship something that…
Read tutorial
When people first hear that an LLM can "use tools," they usually picture the model reaching out and doing something itself—searching the web, running code,…
Read tutorial
The transcript reads clean. The summary reads confident. The wrong name sails through both, and nothing in the text ever flinches.
Read tutorial
A citation is a pointer, not a proof. This drill teaches you to stop trusting the pointer and start reading the span.
Read tutorial
A tool call returns status: "ok". The pipeline moves on. Nobody notices that the result answers a slightly different question than the one the model asked.
Read tutorial
A schema validator turns green, the response parses, and the builder ships it. The answer is still wrong. The check passed because it was never asked to…
Read tutorial
A response that parses is not a response you can trust. Here is a small exercise that turns that sentence into a working habit.
Read tutorial
The model wrote three confident sentences about your screenshot. You still don't know if it actually looked.
Read tutorial
The function looks clean. It reads well. It handles the obvious case. Then it returns the wrong number for "1h30m", and you find out three days later.
Read tutorial
A citation is not proof. It is a pointer — and a pointer is only as trustworthy as the instruction that produced it and the check that verifies it.
Read tutorial
A validator can tell you the shape of an answer. It cannot tell you whether the answer is true.
Read tutorial
You ask an LLM for a list of three book recommendations. What comes back is a friendly paragraph: "If you're looking for something thought-provoking, you…
Read tutorial