AI¶

Build a Second Brain with Claude Code and Obsidian

Most note-taking apps are graveyards. You clip an article, it sits in a folder, you never read it again. The knowledge doesn't connect to anything. It doesn't compound. After three years you have 4,000 notes and can't find anything.

This guide builds something different: a self-maintaining knowledge base where Claude Code acts as your librarian. You dump raw material in. Claude reads it, writes structured wiki articles, cross-links related concepts, and files everything. You ask questions. The answers become new notes. The library grows smarter every time you use it.

The architecture is based on Andrej Karpathy's LLM Wiki pattern: a persistent, compounding knowledge base where an LLM does the bookkeeping you'd never do yourself.

Agent-Driven Software Factory: Replace Vibe Coding With a 12-Agent Pipeline

Vibe coding is not a software development process.

Fire a prompt, accept the result, ship it. Fast in the same way skipping tests is fast — until something breaks and you can't explain why. The output is plausible-looking code with no validated problem, no verified requirements, no threat model, no acceptance tests, no deployment strategy. One feature. Eleven things that were supposed to happen but didn't.

The Software Factory Agent replaces that with a 12-agent pipeline. One developer runs the chain. Specialized agents handle market research, product scoping, UX design, security, implementation, testing, validation, and deployment — each in its own clean context window with only the tools it needs.

Two modes. Discovery mode (12 agents) validates the market, defines the product, and designs the UX before any engineering starts. Feature mode (9 agents) skips straight to implementation for incremental work on an existing product.

The Karpathy Skill: Four Rules That Make You a Better AI-Era Engineer

Most developers use AI coding assistants wrong.

They fire off a vague prompt, accept the first 200-line response, and then spend the next hour debugging why the "helpful" code broke three other things. The tool is fast — the outcome is slow.

Andrej Karpathy — the Stanford AI researcher who co-founded OpenAI, led Tesla's Autopilot team, and built NanoGPT from scratch — distilled decades of engineering intuition into four rules that are now circulating as a CLAUDE.md template for AI coding assistants. These rules are not about AI. They are about how senior engineers think — and they happen to be exactly what you need to get great results from any AI coding tool in 2026.

This post unpacks every rule with the why, concrete examples, and practical habits you can start using today.

Prompt Engineering: The Anthropic Playbook

There is no magic phrase that makes an LLM smarter. There is no secret syntax, no special keyword, no hidden trick that unlocks better results.

What there is: a systematic discipline for giving models what they actually need to do good work. That discipline has a name — prompt engineering — and Anthropic's Harrison Chase and Christiaan Ryan spent an entire workshop teaching it the right way, using a real production example, and showing exactly where simple intuitions fail.

Source: Harrison Chase & Christiaan Ryan, Anthropic — "Prompting 101" (YouTube)

Building Effective AI Agents: The Anthropic Playbook

Most teams building AI agents are solving the wrong problem.

They spend months wiring together orchestration frameworks, reflection loops, and multi-agent graphs — before they've verified that the simplest version of their agent actually works. Then they wonder why the system is expensive, slow, and impossible to debug.

Barry Zhang from Anthropic gave a talk that cuts through all of that. The core message was blunt: most teams are building agents too early, and when they do build them, they build them wrong.

Source: Barry Zhang, Anthropic — "How We Build Effective Agents" (YouTube)

Agentic AI Architectures: Patterns, Frameworks, and MCP for Enterprise Systems

Most AI tutorials show you how to call an API and get a response. That's not an agent. An agent is a system that perceives, plans, acts, and adapts — autonomously — using tools, memory, and other agents to complete tasks that no single LLM call could handle.

In 2026, agentic AI is the dominant paradigm for building AI into enterprise software. Not chatbots. Not search bars with AI behind them. Full autonomous systems that can research a topic, write code, test it, file a ticket, notify a Slack channel, and self-correct when something goes wrong — without a human in the loop for every step.

This is the definitive guide. We cover every design pattern, every major framework, the Model Context Protocol that is quietly unifying the entire ecosystem, and how to wire all of it into production enterprise systems.

GPU for AI Explained: VRAM, CUDA Cores, Tensor Cores, and Everything In Between

You've heard it countless times: "You need a GPU to train AI models." But why? What is a GPU actually doing that a CPU can't? What are CUDA Cores, Tensor Cores, and VRAM — and why do AI engineers obsess over these numbers?

This guide starts from scratch and builds a complete mental model of GPU hardware for AI. By the end, you'll understand exactly what's happening inside the chip when your model trains — and how to pick the right hardware for the job.

Master Generative AI — Part 2: Working with LLMs

Part 2 of the Master Generative AI: A Step-by-Step Challenge series.

Series Map:

• Part 1 → Foundation of AI & ML
• Part 2 → Working with LLMs ← you are here
• Part 3 → Advanced Generative AI
• Part 4 → Practical Applications
• Part 5 → Career & Capstone Projects

In Part 1 you built the conceptual foundation. Now we get our hands dirty. This part is where theory becomes practice — you'll write code that tokenizes text, queries embeddings, builds a RAG pipeline, and ships your first working chatbot.

MCP vs Tool Calling vs Skills: The Mental Model Every AI Builder Needs in 2026

You're building an AI agent. You've heard the terms thrown around — tool calling, MCP, skills — and nobody has given you a clean mental model for how they fit together. Are they competing approaches? Different names for the same thing? Should you pick one?

Here's the answer in one sentence: they are layers, not alternatives. Tool calling is the primitive. MCP is the protocol. Skills are the playbook. Production agents in 2026 use all three.

Building an LLM from Scratch in PyTorch: The Full Lifecycle Cheatsheet

Most LLM tutorials give you one of two things: a high-level diagram with boxes and arrows, or a 10,000-line codebase with no explanation of why each piece exists.

This post is neither. It's a step-by-step lifecycle — 8 phases, each with working PyTorch code, the reasoning behind every decision, and an explicit Do / Don't list that captures the mistakes that cost most beginners weeks of wasted compute.

By the end you'll have built, trained, modernised, scaled, and aligned a language model — the exact same lifecycle that produced every major LLM you've used.

Phase 1: Core Transformer    → the engine
Phase 2: Train a Tiny LLM    → prove the pipeline works
Phase 3: Modernise           → match 2026 architecture
Phase 4: Scale Efficiently   → push past toy datasets
Phase 5: Mixture of Experts  → conditional computation
Phase 6: SFT                 → turn autocomplete into an assistant
Phase 7: Reward Modelling    → teach the model what "good" looks like
Phase 8: RLHF                → optimise for human preference