AI Agents & Agentic AIWhat AI agents are, how they reason and act, and why agentic AI is reshaping how software gets built.
MCP — Model Context ProtocolThe open standard that lets AI agents connect to databases, APIs, and tools. USB for AI — write once, works with any model.
Physical AIAI in robots, autonomous vehicles, and edge devices. How AI is moving from screens into the physical world.
Risks of Agentic AICompounding errors, prompt injection, cost runaway, jailbreaking — the real challenges of deploying autonomous AI agents safely.
What is AI Harness Engineering?Evaluation harnesses for AI — systematic frameworks to test, benchmark, and validate LLMs, RAG pipelines, and agents before and after production.
Evaluation Frameworkslm-evaluation-harness, HELM, OpenAI Evals, DeepEval, and Promptfoo — the tools used to benchmark and compare AI models.
Benchmark DatasetsMMLU, HumanEval, GSM8K, BIG-Bench, GPQA — the standard benchmarks explained, plus how to build your own golden evaluation dataset.
RAG EvaluationEvaluate retrieval and generation separately using Ragas and TruLens. Faithfulness, answer relevancy, context recall, and context precision metrics.
Automated Eval PipelinesWire evaluation into CI/CD with GitHub Actions. Auto-block deploys when quality scores drop below threshold.
Red Teaming & SafetySystematically test for prompt injection, jailbreaks, toxicity, and bias using Garak and adversarial prompt datasets.
Performance BenchmarkingMeasure TTFT, total latency, cost per request, and throughput. Compare models on speed and price before committing.
Regression TestingDetect quality degradation from model updates, prompt changes, or retrieval changes using baselines and A/B evaluation.
Complete IDEs rebuilt from the ground up around AI — not extensions bolted onto an existing editor.
CursorThe leading AI-native IDE. A VS Code fork rebuilt around AI with codebase-aware chat, Composer agent mode, and your choice of Claude, GPT, Gemini, or Grok.
WindsurfAI-first IDE from Codeium. Cascade agentic editing understands your full project context. Supercomplete predicts your next edit, not just the next line.
AWS KiroAmazon's AI IDE with spec-driven development. Generates a full requirements spec before writing a single line of code. Built-in MCP, Hooks, and steering files.
AI extensions and agents that work inside VS Code, Visual Studio, JetBrains, or Vim — without switching editors.
GitHub CopilotThe world's most-used AI coding extension. Works inside VS Code, Visual Studio, JetBrains, and Vim. Inline completions, chat, and Agent Mode.
Claude for VS CodeAnthropic's Claude extension for VS Code. Chat with Claude about your open files, get inline suggestions, and run Claude Code from within the editor.
Codex in VS CodeOpenAI's Codex powers GitHub Copilot and is also available as an extension. Inline completions and chat directly inside your editor.
Dedicated AI tools that are not full IDEs — they run in your terminal, browser, or as a separate app alongside your existing workflow.
Claude CodeAnthropic's terminal AI agent. Runs in your terminal alongside any editor — reads your codebase, edits files, runs tests, and commits changes autonomously.
OpenAI Codex (Agent)OpenAI's cloud-based coding agent. Runs tasks in a sandboxed environment, opens GitHub PRs, and executes multiple tasks in parallel.
Google Anti-GravityGoogle's standalone AI coding tool, now powered by Gemini 4. Large token context, Google Search grounding. Not an IDE — a separate AI coding app.
Gemini CLIGoogle's open-source terminal AI agent. Free tier with 1M token context and Google Search grounding. Runs in any terminal alongside your editor.
MySQLMySQL fundamentals, joins, indexes, stored procedures, replication, and optimisation techniques.
Oracle DatabaseOracle SQL, PL/SQL, partitioning, and interview questions for Oracle-based enterprise systems.
SSIS — SQL Server Integration ServicesTen deep-dive ETL guides: control flow, data flow internals and buffers, error handling, performance engineering, incremental loads and CDC, SSISDB operations, CI/CD, and modernisation.
Quiz HubTest your knowledge across Python, JavaScript, TypeScript, C#, Docker, Azure, and GitHub Copilot. 300+ questions with instant feedback and explanations.
Python Quiz60 questions across fundamentals, OOP, async, type hints, iterators, testing, and memory management.
JavaScript Quiz60 questions covering closures, async/promises, ES6+ features, the DOM, and modern tooling.
TypeScript Quiz40 questions on the type system, generics, utility types, and advanced TypeScript patterns.
C# & .NET Quiz60 questions on OOP, LINQ, async/await, generics, memory management, and ASP.NET Core.
Docker & Kubernetes Quiz40 questions on containers, images, networking, volumes, and Kubernetes fundamentals.
Azure Cloud Quiz40 questions aligned with AZ-900 to AZ-204 — compute, storage, networking, identity, and DevOps.
GitHub Copilot Quiz60 questions on Copilot features, best practices, enterprise usage, and certification prep.
Use the left sidebar to browse all sections, or use search to jump directly to any topic.