Learn It Fast

Interactive Learning

Step-by-Step Simulators

Interactive simulators covering LLM internals, RAG, agents, cloud platforms, cost, and safety. Use ▶ Play to auto-advance, ↺ Reset to replay. Filter by category below to jump to a topic.

You're on the Free plan.

Unlock every simulator, plus cheat-sheets and certificates, with Pro.

See plans
Topic
Level

LLM Families Compared

Four columns — Claude, GPT, Gemini, and Llama — stepped through architecture (dense vs MoE), tokenisers, attention variants (MHA/GQA/MLA), training recipes, context windows, and licensing.

🎮LLM Families Compared — Claude · GPT · Gemini · LlamaLLM fundamentals

Claude (Anthropic)

Dense transformer · RLHF + Constitutional AI · strong at tool use & long context

GPT (OpenAI)

MoE frontier models · heavy RLHF · broadest tool/function-call ecosystem

Gemini (Google DeepMind)

Natively multimodal MoE · huge context (1M–2M) · tight Google grounding

Llama (Meta)

Open-weights dense + MoE · you host it · full fine-tune & quantize freedom

Four families dominate production LLMs today. One-line positioning before we dive into the internals.

1 / 7

CI/CD Pipeline

Step a commit through a delivery pipeline — build (with caching), parallel tests, quality gates, and deploy with manual approval and rollback. Includes a hosted (GitHub Actions / CircleCI) vs self-managed (Jenkins) comparison and the DORA metrics.

🎮DevOps & DeliveryDevOps 101

Difficulty: intermediate

Duration: 12 min

📝 Pipeline Config

# .github/workflows/ci.yml — the job graph
name: CI/CD
on: [push, pull_request]

jobs:
  build:
    runs-on: ubuntu-latest
    steps: [ ... ]

  test:
    needs: build          # waits for build
    runs-on: ubuntu-latest
    steps: [ ... ]

  deploy:
    needs: test           # only if tests pass
    if: github.ref == 'refs/heads/main'
    runs-on: ubuntu-latest
    steps: [ ... ]

Stages

build → test → deploy

Trigger

push / PR

Typical run

4–8 min

💡 Explanation

A pipeline is the **automated path from commit to production**. Each stage gates the next via `needs:` — tests only run if the build succeeds, deploy only runs if tests pass.

• **CI** (Continuous Integration): build + test every change. • **CD** (Continuous Delivery/Deployment): promote passing builds toward prod. • The whole graph runs on every push; a red stage stops the line.

1 / 8

RAG Pipeline

Retrieval-Augmented Generation grounds LLM responses in your own documents. Watch how a user query travels through embedding, vector search, context injection, and grounded generation — step by step.

Pro simulator

RAG Pipeline is part of Pro

Unlock all simulators — including advanced cost, safety, RAG, and multi-agent patterns — plus downloadable cheat-sheets and certificates.

MCP Call Flow

The Model Context Protocol standardises how hosts, clients, and servers communicate. Trace the full JSON-RPC lifecycle from TCP connection through tool discovery, tool call, execution, and final response.

Pro simulator

MCP Call Flow is part of Pro

Unlock all simulators — including advanced cost, safety, RAG, and multi-agent patterns — plus downloadable cheat-sheets and certificates.

ReAct Agent Loop

ReAct agents interleave Thought (chain-of-thought reasoning) with Action (tool calls) and Observation (results) until they have enough information to produce a final answer. Watch the scratchpad grow as the agent loops.

Pro simulator

ReAct Agent Loop is part of Pro

Unlock all simulators — including advanced cost, safety, RAG, and multi-agent patterns — plus downloadable cheat-sheets and certificates.

Cloud Platform Comparison

Quick visual refresher for interviews — one agent-building scenario walked through all three major clouds side-by-side: Amazon Bedrock, Google Vertex AI, and Azure AI Foundry. Covers auth, model catalogs, agent primitives, tool formats, and RAG.

Pro simulator

Cloud Platform Comparison is part of Pro

Unlock all simulators — including advanced cost, safety, RAG, and multi-agent patterns — plus downloadable cheat-sheets and certificates.

Inside a Transformer

What actually happens when you send a prompt? Walk a concrete sentence through tokenisation, embedding, attention, feed-forward networks, the layer stack, logits, and sampling — with real-looking numbers at every step.

Pro simulator

Inside a Transformer is part of Pro

Unlock all simulators — including advanced cost, safety, RAG, and multi-agent patterns — plus downloadable cheat-sheets and certificates.

Model Parameters Playground

Interactive — drag the sliders to see exactly how temperature, top_k, top_p, and the penalty knobs reshape the next-token probability distribution.

Pro simulator

Model Parameters Playground is part of Pro

Unlock all simulators — including advanced cost, safety, RAG, and multi-agent patterns — plus downloadable cheat-sheets and certificates.

Tool-Use Loop

Follow a single user question through the full loop — user → model → tool_use → tool result → final answer — with a live token budget sidebar showing why multi-step agents cost so much more than a single chat completion.

Pro simulator

Tool-Use Loop is part of Pro

Unlock all simulators — including advanced cost, safety, RAG, and multi-agent patterns — plus downloadable cheat-sheets and certificates.

Prompt Caching

Five requests, same 12k-token system prompt. Watch the cache miss → write → hit → TTL expiry → rewrite pattern play out, with a running bill that shows exactly when caching pays for itself.

Pro simulator

Prompt Caching is part of Pro

Unlock all simulators — including advanced cost, safety, RAG, and multi-agent patterns — plus downloadable cheat-sheets and certificates.

RAG Chunking Strategies

Same document, same query, four chunking strategies: fixed-size, recursive, semantic, and hierarchical. See which chunks the retriever surfaces — and which strategy wins on this query.

Pro simulator

RAG Chunking Strategies is part of Pro

Unlock all simulators — including advanced cost, safety, RAG, and multi-agent patterns — plus downloadable cheat-sheets and certificates.

Cost Calculator

Pick a model tier, dial in your traffic, input/output sizes, and cache hit rate — get a live monthly bill with a cost-breakdown bar and "savings vs no-cache" delta.

Pro simulator

Cost Calculator is part of Pro

Unlock all simulators — including advanced cost, safety, RAG, and multi-agent patterns — plus downloadable cheat-sheets and certificates.

Prompt Injection — Attack & Defense

A KB document has been poisoned with an injection. Toggle defenses (delimiters, spotlighting, output validation, low-priv summariser) and see which combinations stop the agent from exfiltrating customer data.

Pro simulator

Prompt Injection — Attack & Defense is part of Pro

Unlock all simulators — including advanced cost, safety, RAG, and multi-agent patterns — plus downloadable cheat-sheets and certificates.

Multi-Agent Orchestration

An orchestrator fans out to Researcher, Outliner, Writer, and Editor subagents to produce a blog post. Watch the graph light up, messages stream in, and the token budget climb — then compare four orchestration patterns side-by-side at the end.

Pro simulator

Multi-Agent Orchestration is part of Pro

Unlock all simulators — including advanced cost, safety, RAG, and multi-agent patterns — plus downloadable cheat-sheets and certificates.

Agent Frameworks Compared

Step through the same customer support task in CrewAI, LangChain, and LangGraph side-by-side. See how each framework structures the agent, tools, and execution loop differently — then choose which one fits your thinking style.

Pro simulator

Agent Frameworks Compared is part of Pro

Unlock all simulators — including advanced cost, safety, RAG, and multi-agent patterns — plus downloadable cheat-sheets and certificates.

Prompt Engineering Patterns

Five prompt engineering patterns that reshape quality and cost: few-shot vs zero-shot, chain-of-thought reasoning, structured output, prompt caching, and complexity trade-offs. Compare their latency, accuracy, and cost side-by-side.

Pro simulator

Prompt Engineering Patterns is part of Pro

Unlock all simulators — including advanced cost, safety, RAG, and multi-agent patterns — plus downloadable cheat-sheets and certificates.

RAG Patterns & Strategies

Four advanced RAG patterns: chunking strategies (fixed, recursive, semantic), retrieval methods (BM25, vector, hybrid, reranking), scaling laws (corpus size impact), and failure modes (hallucination, context mismatch, latency). Learn when each technique wins.

Pro simulator

RAG Patterns & Strategies is part of Pro

Unlock all simulators — including advanced cost, safety, RAG, and multi-agent patterns — plus downloadable cheat-sheets and certificates.

Multi-Agent Patterns

Four multi-agent design patterns: handoff strategies (Swarm vs LangGraph vs CrewAI), tool routing (manual vs classifier vs function-calling), communication protocols (direct, shared memory, blackboard, events), and failure modes with recovery strategies.

Pro simulator

Multi-Agent Patterns is part of Pro

Unlock all simulators — including advanced cost, safety, RAG, and multi-agent patterns — plus downloadable cheat-sheets and certificates.

Production Patterns

Three patterns engineers ship without and regret: Evals (LLM-as-judge, golden datasets, CI gates), Observability (OpenTelemetry traces with token + cost attribution), and Context Compaction (the new beta for keeping long-running agents alive past 1M tokens).

Pro simulator

Production Patterns is part of Pro

Unlock all simulators — including advanced cost, safety, RAG, and multi-agent patterns — plus downloadable cheat-sheets and certificates.

Reasoning Models

How o1, DeepSeek R1, and Claude extended thinking differ from standard completions. Trace the internal thought scratchpad, see how the token budget controls cost, and learn which task types earn the reasoning premium.

Pro simulator

Reasoning Models is part of Pro

Unlock all simulators — including advanced cost, safety, RAG, and multi-agent patterns — plus downloadable cheat-sheets and certificates.

LLM Fine-Tuning

Walk the full fine-tuning pipeline — dataset prep, full fine-tuning vs LoRA/QLoRA, the training loop, RLHF, and before/after evaluation. Includes cost estimates and regression benchmarks.

Pro simulator

LLM Fine-Tuning is part of Pro

Unlock all simulators — including advanced cost, safety, RAG, and multi-agent patterns — plus downloadable cheat-sheets and certificates.

Neural Networks & Backprop

Build a network from scratch — forward pass, loss, the chain-rule gradient flow, weight updates, and the Adam optimiser. The same loop that trains GPT-4, just with 16 parameters instead of 1.8 trillion.

Pro simulator

Neural Networks & Backprop is part of Pro

Unlock all simulators — including advanced cost, safety, RAG, and multi-agent patterns — plus downloadable cheat-sheets and certificates.

AI in Cybersecurity

Both sides of the AI/security divide — adversarial examples, AI-powered phishing, anomaly detection, deepfake detection, and defensive AI red teaming. Covers attack patterns and concrete defences.

Pro simulator

AI in Cybersecurity is part of Pro

Unlock all simulators — including advanced cost, safety, RAG, and multi-agent patterns — plus downloadable cheat-sheets and certificates.

Streaming Data Pipelines

Real-time AI data infrastructure: Kafka event ingestion → Flink stream processing → feature store → online model serving. With drift detection and automated retraining triggers.

Pro simulator

Streaming Data Pipelines is part of Pro

Unlock all simulators — including advanced cost, safety, RAG, and multi-agent patterns — plus downloadable cheat-sheets and certificates.

n8n AI Workflow Automation

Visual node-graph AI agent orchestration with n8n — AI Agent nodes, webhook triggers, multi-step workflows, and a side-by-side comparison with LangChain and CrewAI to help you pick the right tool.

Pro simulator

n8n AI Workflow Automation is part of Pro

Unlock all simulators — including advanced cost, safety, RAG, and multi-agent patterns — plus downloadable cheat-sheets and certificates.

WireGuard VPN & Networking

Secure AI infrastructure with WireGuard — modern vs legacy VPN protocols, key exchange, tunnel configuration, split tunnelling, and a complete hub-and-spoke topology for protecting GPU clusters and training data.

Pro simulator

WireGuard VPN & Networking is part of Pro

Unlock all simulators — including advanced cost, safety, RAG, and multi-agent patterns — plus downloadable cheat-sheets and certificates.

Prompt Whisperer

See how small prompt changes dramatically improve AI output. Watch the same request evolve from vague to excellent across three scenarios — email writing, explaining concepts, and brainstorming. No jargon, just results.

Pro simulator

Prompt Whisperer is part of Pro

Unlock all simulators — including advanced cost, safety, RAG, and multi-agent patterns — plus downloadable cheat-sheets and certificates.

AI for My Job

Pick your role — marketer, teacher, HR, finance, healthcare, or designer — and discover real AI use cases, estimated time savings, and copy-paste prompts tailored to your day-to-day work.

Pro simulator

AI for My Job is part of Pro

Unlock all simulators — including advanced cost, safety, RAG, and multi-agent patterns — plus downloadable cheat-sheets and certificates.

Hallucination Detector

AI makes things up — confidently. Read AI-generated passages on history, medicine, and books, then spot the fabricated claims before they're revealed. Learn why AI hallucinates and how to catch it.

Pro simulator

Hallucination Detector is part of Pro

Unlock all simulators — including advanced cost, safety, RAG, and multi-agent patterns — plus downloadable cheat-sheets and certificates.

AI Ethics Dilemmas

Face five real-world AI dilemmas — a biased hiring algorithm, a medical AI with equity gaps, content moderation at scale, surveillance cameras, and self-driving car ethics. Choose your response and see the trade-offs.

Pro simulator

AI Ethics Dilemmas is part of Pro

Unlock all simulators — including advanced cost, safety, RAG, and multi-agent patterns — plus downloadable cheat-sheets and certificates.