Skip to content

Internals Decoded

Home About UsWork With UsSubscribe

Opening the library

Internals Decoded

A technical publishing studio for AI. Free to read, and there is a lot of it.

Articles·Series·Start Here·Learn·About·Work with us·Newsletter·Privacy·Terms

Written by the Internals Desk. admin@internalsdecoded.com

© 2026 Internals Decoded. Built for anyone curious about what really goes on inside AI.

Articles

Everything we know, handed over.

Deep dives into the internals of modern AI. Every piece is free to read in full, with nothing held back for a signup.

⌕

112 articles found

A Recipe the Machine Follows

A program is a recipe for a very literal cook. Meet the algorithm, with no code in sight.6 min
Beginner Deep Dives

Agent Memory: The Four Kinds and How They Fit Together

LLMs forget everything between calls. In-context, external, episodic, and semantic memory fix that.8 min
Advanced Deep Dives

Agentic RAG: When the Retriever Starts Thinking

Query rewriting, multi-step retrieval, and agents that decide what to look up.13 min
Intermediate Explainers

AI Benchmarks, Explained: What MMLU and Friends Actually Measure

How to read a benchmark table without being fooled by it.10 min
Beginner Playbooks

AI for Documents and Spreadsheets That Actually Saves Hours

Drafting, summarizing, cleaning data, and building formulas with AI, step by step.10 min
Beginner Playbooks

AI for Meetings and Email: Reclaim Your Calendar

Notes, action items, drafts, and follow-ups on autopilot, without sounding like a robot.10 min
Beginner Playbooks

AI Privacy at Work: What You Can and Can't Paste

Company data, customer data, and AI tools: the rules that keep you out of trouble.9 min
Beginner Explainers

Attention, Gently: How Models Decide What Matters

The mechanism behind the magic, explained with zero math.14 min
Beginner Deep Dives

Batching and PagedAttention: How vLLM Serves Thousands at Once

Continuous batching and paged memory: the two ideas behind modern serving throughput.11 min
Advanced Explainers

Breaking Language Into Pieces

Before a model reads text, it chops it into pieces. Meet the token and the tokenizer.4 min
Beginner Protocols

Build Your First MCP Server

Tools, resources, and prompts: a working server from scratch, explained line by line.11 min
Intermediate Playbooks

Building Your Personal AI Stack

A concrete, affordable setup for professionals, from free tier to power user.10 min
Beginner Explainers

Careful or Adventurous

Should a model play it safe or take a risk on its next word? The temperature dial, explained.5 min
Beginner Playbooks

Chain of Thought: When Thinking Out Loud Helps

Step-by-step reasoning improves hard tasks and wastes tokens on easy ones. Know the difference.11 min
Intermediate Deep Dives

Chunking: The Decision Everything Downstream Inherits

Sizes, overlap, and semantic boundaries. Get this wrong and nothing after it can save you.20 min
Intermediate Playbooks

Claude Code + Your IDE: A Workflow That Compounds

Where the terminal agent beats the IDE, where it doesn't, and how to run both for maximum output.9 min
Intermediate Playbooks

Claude Code vs Cursor: How Each One Thinks

Terminal agent vs AI-native IDE: context strategies, strengths, and the tasks each wins.9 min
Intermediate Playbooks

CLAUDE.md: How Claude Code Thinks About Your Project

The one file that changes everything: project memory, conventions, and context strategy.8 min
Intermediate Deep Dives

Context Window Management for Big Jobs

Chunking, map-reduce, and retrieval: how agents handle work that never fits in one context window.14 min
Advanced Deep Dives

Context Windows Are Not What You Think

A million tokens on the label doesn't mean a million tokens of attention. Lost-in-the-middle, explained.12 min
Intermediate Explainers

Context Windows: The Model's Working Memory

What fits, what falls out, and why long conversations get weird.9 min
Beginner Deep Dives

Debugging Agent Systems: Traces, Replays, Root Causes

Agent failures raise no errors. The logging, tracing, and replay toolkit that makes them debuggable.11 min
Advanced Playbooks

Designing Your Personal AI Coding Workflow

A concrete system: which tool, which task, which guardrails, and when to just write it yourself.16 min
Intermediate Explainers

Diffusion: How Image Generators Actually Draw

Noise, denoising, and guidance: the process behind every generated image you've seen.10 min
Advanced

The Newsletter

Keep up with AI. One email a week.

Email address

One thoughtful email each week. Unsubscribe whenever you like. Read our privacy policy.