AI Tutorials & Practice

...but let me say this right away: coding was never the most valuable part of software...

A user clicks “Run agent”, your backend receives a normal HTTP request, and the agent starts doing...

Let me describe a moment you've had recently, and be honest that I've had it too. A pull request...

An observability-first approach for building an AI agent, and what it bought me. A couple of weeks...

There's a new visitor in your logs: the AI agent, acting on someone's behalf. Right now it "uses"...

i wrote this while claude wrote the code. its 3am. fix agent is running for the third time, i have...

I was closing out a throwaway repo from an agent-workflow experiment. I had treated experiment repos...

Open WebUI is one of the first tools that appeared in conjunction with Large Language Models....

I published two articles three weeks apart. They were not about the same thing. The first was about...

A few months back I sat in a meeting where someone said, dead serious, "we should fine-tune the RAG."...

A backend engineer closed a laptop lid on a crowded commuter train and expected a local coding agent...

You've read this sentence, or something close to it: RoPE handles longer sequences than absolute...

Every market report on Earth agrees: there are about 30 million software developers on the...

TinyStories is famous for a ~1,500-word vocabulary, so I capped mine at 1,500 and scored every arm on identical positions. It came out 4 points worse at top-1 than a 4,000-word cap, and more than a third of its output was the unknown-word …

For twelve days, every scheduled job fired, every commit gate passed, and the label on the front of...

Update — v0.2.0 released. CauterRule is now live on GitHub and PyPI. It turns repeated agent...

Come to check the locks, and leave holding the keys. Slip in through the gap, take the host's seat,...

The word was qara, "black". I fed it to an off-the-shelf TTS model, hit play, and got back a soft,...

Three parties describe the same roof and none of them can read the others' description. The town...

For two weeks, a small group of strangers on a GitHub issue about agent auto-memory audited one file:...

Anthropic has disclosed three real-world cybersecurity incidents in which Claude models reached...

The first time an n8n AI workflow fails, it often does not fail cleanly. It returns a 200 status...

The dangerous AI workflow is not the one that says, “I don’t know.” It is the one that gives a...

An n8n workflow can receive a webhook, call an LLM, query a database, enrich a CRM record, store a...

Open an n8n workflow with 40 nodes and two thoughts usually appear at the same time. First: This is...

Perhaps you've heard the term Loop Engineering: instead of solving a problem by hand, you build a...

An agentic RAG system can do something a simple retrieval pipeline cannot: notice missing evidence,...

Most RAG failures are not model failures. The model did not forget how to read. The prompt is not...

The first time a RAG system gets a large knowledge base, it often does not fail loudly. It gets...

Your RAG system can retrieve the “right” document and still give the wrong answer. The document may...

Your RAG system did not fail because the model hallucinated. It failed because the only “facts” the...

You check the logs. The vector search returned the exact policy document the user asked about. The...

An AI agent that works can complete a task. An AI agent you can trust can do something harder: it...

Most agent failures are not model failures. They are loop failures. The model may be smart enough....

Almost every RAG evaluation metric on offer needs a language model to produce it. Faithfulness,...

Free-tier inference can draft a plan, a schema comment, even a chain of thought that looks like...

Two posts ago msgboard.dev was a toy. One post ago it was a prompt-injection honeypot. This post is...

METR found spoofed tool calls in 7% of agent transcripts from the Hugging Face incident. A transcript monitor reads them as clean. Diff against a...

On a Tuesday incident call, a backend engineer pasted an agent transcript and declared the webhook...

For a while now I have used LLMs to automate parts of my work. One of those parts is debugging hard...