AI, LLM & Agentic Systems
LLM internals, tokenization, model training, RAG, agent architectures, evals, safety, and production AI system design.
Courses
Learn how to design scalable, reliable, and maintainable systems — from single servers to distributed architectures used by millions of users.
Master 60+ essential AI, LLM, RAG, agentic, fine-tuning, safety, and LLMOps terms with architectural diagrams, code examples, self-checks, and exercises.
Prepare for Anthropic's Claude Certified Associate – Foundations exam: prompting, checking Claude's output, choosing models and features, workflows, Projects, governance and troubleshooting. 25 lessons, each with a video, exam traps and self-checks. No coding needed.
Articles
Anthropic runs four role-based Claude certifications: Associate – Foundations, Developer – Foundations, Architect – Foundations and Architec…
One of the most persistent frustrations in AI-assisted development is API Drift. You ask an AI coding assistant to write a Next.js 15 route,…
Most multi-agent software engineering frameworks suffer from the same fatal flaw: they treat coding as a simulated conversational chat. Fram…
Large Language Models (LLMs) are often described as black boxes, yet their behavior is the direct outcome of a deterministic, multi-stage en…
Software engineering has undergone a fundamental architectural shift. The era of inline tab-autocomplete copilots has given way to autonomou…
Claude Code can run shell commands, edit files, and fetch URLs. Permission rules decide which of those actions run without asking, which pro…
The Claude Code CLI has grown from claude plus a few convenience flags into a full control surface: interactive sessions, one-shot SDK-style…
Claude Code reads configuration from a small set of files in your project and in ~/.claude, and writes session data to ~/.claude as it works…
Claude Code is billed by tokens, and its token use is driven less by how much you type than by how much context it carries: every request se…
A security review of Claude Code has to answer two kinds of question. What happens to our data once it leaves the laptop: is it used for tra…
The Claude Agent SDK gives your own programs the same agent loop that runs Claude Code: you call query() with a prompt and options, and Clau…
Two Claude Code sessions in the same checkout edit the same files, and sooner or later one overwrites the other's work or runs the tests in …
Running several Claude Code sessions in separate terminals works until you lose track of which one is waiting for you. Agent view, opened wi…
Some tasks are bigger than one conversation can coordinate: audit every route handler for missing auth checks, migrate 500 files, cross-chec…
An agent that runs for four seconds inside one HTTP request can afford to fail: the user retries and nothing else happened. An agent that ru…
A base language model finishes text. It does not answer questions, refuse harmful requests, or stop talking at the right moment — those beha…
A 70B-parameter model does not fit on an 80GB GPU, and the reason is not the parameters. In mixed-precision training with Adam you carry rou…
Claude Code reads configuration from a small set of files in your project and in ~/.claude, and writes session data to ~/.claude as it works…
Claude Code is an agent that works in your project: it reads files, edits them, and runs commands such as your test suite. That makes the fi…
Claude Code follows your CLAUDE.md most of the time. A hook makes something happen every time. Hooks are shell commands (or HTTP calls, prom…
Artificial intelligence terminology moves so fast that concept definitions quickly become bloated with marketing fluff and overlapping jargo…
AI coding agents change where engineering effort is spent: the hard problem moves from typing code to defining boundaries, checking outputs,…
Claude Code has a dense vocabulary because it is more than a chat box beside your editor. The important terms describe where the model runs,…
Claude Code is an agentic coding tool that can inspect a repository, propose edits, run permitted commands, and work through a task in a ter…
Claude Code can run shell commands, edit files, and fetch URLs. Permission rules decide which of those actions run without asking, which pro…
Every request Claude Code sends to the model carries the whole session so far: the system prompt, your CLAUDE.md files, every message, every…
Organisations that run Claude through Amazon Bedrock, Google Cloud, or Microsoft Foundry, often for data-residency reasons, used to face a c…
Manual permission prompts protect you only while you read them. After the twentieth "Allow npm test?" in a refactoring session, most people …
Plan mode is the Claude Code permission mode for thinking before touching code. Claude reads files, runs commands to explore, and writes a p…
A CLAUDE.md file is where you write down what you would otherwise re-explain to Claude Code every session: the build command it cannot guess…
A Claude Code skill is a folder with a SKILL.md file: YAML frontmatter that says what the skill is for, and markdown instructions Claude fol…
The Model Context Protocol (MCP) is an open protocol for exposing tools, resources, and prompts to AI applications over JSON-RPC 2.0. One se…
In a small repository, Claude Code's defaults work: one CLAUDE.md, launch from the root, let it search. In a monorepo with dozens of package…
The Claude Code CLI has grown from claude plus a few convenience flags into a full control surface: interactive sessions, one-shot SDK-style…
A team building an internal tool that reviews pull requests, runs the test suite, and posts a summary comment reaches for "Claude" and finds…
Close a Claude Code session mid-task and the natural fear is that you just lost an afternoon of debugging context — the files it read, the f…
Open a chat with an LLM and ask it to fix a bug, and the best you get back is a suggested diff you copy into your editor by hand — the model…
A language model does not output text. At each step it outputs one score per vocabulary token, and a separate piece of code, the sampler, tu…
BM25 is a ranking function from the 1990s that still runs behind Lucene, Elasticsearch and OpenSearch, and it is still the baseline that new…
An AI agent that calls tools sounds like it needs a framework. It doesn't. The model never runs anything itself: it returns a structured req…
Model APIs fail in ordinary ways: rate limits, overloaded capacity, server errors, dropped connections and calls that run longer than a time…
Every few months a new system gets called a "world model" — Genie generating playable game worlds from a single image, Sora producing minute…
Tell an agent to book a one-way flight from Seattle to Austin and the airline has no public booking API — the only way in is the same websit…
You have probably seen a claim shaped like this on a model card: "70B total parameters, but only 13B active per token." That is not marketin…
LangChain, LlamaIndex, and the Claude Agent SDK all help you build applications where a model calls tools, but they start from different cen…
"MCP or OpenAPI?" is a common question when connecting AI agents to tools, and it is slightly the wrong question. The Model Context Protocol…
Asking a model to "reply in JSON" works until it does not: a missing field, a trailing comment, a number returned as a string, a polite sent…
Google's Gemini CLI is an open-source coding agent for the terminal. Three mechanisms decide what it knows and what it can do: context files…
Modern coding agents are no longer just chat boxes beside your editor. The useful power comes from controls around the loop: commands you ca…
Every agentic coding session forces a trade-off: the more autonomy you give the agent, the faster it moves, and the harder it is to catch a …
Running one AI coding agent on a task is easy. The moment you want three or thirty of them working at once — without two agents editing the …
Timeline slides about Claude Code usually stack five gold dates and call it a rise. Dates are useful only when you ask what capability bound…
An issue says ORD-142: checkout-api resets after 30 seconds. Every AI coding product claims it can fix the bug, run tests, and open a pull r…
A support ticket that needs docs, a tool call, and a model reply does not need twelve equal "frameworks." It needs an orchestration lane, a …
AI agents rarely work alone. They read files, query databases, call business APIs, and sometimes delegate work to other agents. Without shar…
A prompt is only one part of a production AI system. Engineers also need vocabulary for execution loops, tool connections, model access, cos…
A chatbot answers one prompt at a time. An agentic AI system accepts a goal, selects actions, calls tools, observes results, and loops until…
Artificial intelligence is not here to replace .NET developers. It is here to extend what they can build. The fundamentals you already know …
Want a guided sequence? Follow a learning path that includes this topic.
View Learning Paths