TechnologyPlanned

AI Tools & Concepts

Complete guide for software engineers — from how LLMs work to building with AI APIs, agents, and RAG

Started April 9, 2026
Target: June 1, 2026
Updated April 9, 2026
Overall Progress0%
Done
In progress
Not started
0/20 topics

Part 1 — Core Concepts

Upcoming0/6
What Are LLMs

What large language models actually are, how they think

Tokens & Tokenization

What tokens are, why they matter, how to count them, cost

Context Window

What it is, why it's limited, how to manage it, pricing

Temperature, Top-P & Sampling

How AI generates text, randomness controls, when to tune

Embeddings & Vector Search

How AI understands meaning, similarity search, RAG basics

Fine-Tuning vs Prompting vs RAG

Three ways to customize AI, when to use which

Part 2 — Prompting & Getting the Best Output

Upcoming0/3
Prompt Engineering Fundamentals

Zero-shot, few-shot, chain-of-thought, system prompts

Advanced Prompting Techniques

ReAct, tree-of-thought, self-consistency, structured output

System Prompts & Instructions

How to write effective system prompts, persona, constraints

Part 3 — AI Tools Ecosystem

Upcoming0/4
Claude (Anthropic)

Models, features, API, Claude Code, artifacts, projects

ChatGPT & OpenAI

GPT-4o, o1/o3, API, plugins, custom GPTs

AI Coding Assistants

GitHub Copilot, Cursor, Windsurf, Cline, Claude Code

Open Source Models

Llama, Mistral, Gemma, DeepSeek, running locally

Part 4 — Building With AI

Upcoming0/5
AI APIs & SDKs

Anthropic API, OpenAI API, structured output, streaming

Tool Use & Function Calling

How AI calls tools, MCP protocol, agentic patterns

AI Agents

What agents are, agent loops, multi-agent systems, frameworks

RAG (Retrieval-Augmented Generation)

Vector DBs, chunking, retrieval, end-to-end RAG pipeline

Evaluations & Testing AI

How to measure AI quality, evals, benchmarks, red-teaming

Part 5 — Staying Current

Upcoming0/2
AI Landscape & Key Players

Who's who, model comparison, pricing, capabilities

AI News & Updates

Latest AI announcements and developments

Notes & Resources

Key Terms Quick Reference

TermDefinition
LLMLarge Language Model — neural network trained on text to generate text
TokenSmallest unit of text the model processes (~4 chars or ~3/4 of a word)
Context WindowMaximum tokens the model can see at once (input + output)
TemperatureControls randomness: 0 = deterministic, 1 = creative
EmbeddingVector representation of text that captures meaning
RAGRetrieve relevant docs, feed them to LLM for grounded answers
AgentAI that can use tools, make decisions, and take actions in a loop
MCPModel Context Protocol — standard for connecting AI to tools/data