Free interview guidesNo signup to read
Learn with DevInterviewMaster
Free, in-depth interview guides — agentic AI patterns, AI & automation, and system design. Answer-first, diagram-minded, grounded in real interview questions.
161 free guides3 tracksAnswer-first · Interview-ready
Agentic AI Design Patterns
26 free guides
Orchestration, memory, guardrails, and multi-agent protocols — the patterns behind production AI agents.
- Agent-to-Agent Communication (A2A)
- Anatomy of an Agent: Brain, Tools, Memory
- Evaluation & Observability
- Evaluator-Optimizer Pattern
- Exception Handling & Recovery
- Exploration & Discovery
- Goal Setting & Monitoring
- Guardrails & Safety
Show all 26 guides
- Human-in-the-Loop Pattern
- Learning & Adaptation
- Memory Management Pattern
- Model Context Protocol (MCP)
- Multi-Agent Collaboration
- Orchestrator-Workers Pattern
- Parallelization Pattern
- Planning Pattern (Plan, then Execute)
- Prioritization
- Prompt Chaining Pattern
- RAG: Retrieval-Augmented Generation
- ReAct Pattern (Reason + Act)
- Reflection Pattern (Self-Critique)
- Resource-Aware Optimization (Cost & Latency)
- Routing Pattern
- Tool Use Pattern (Function Calling)
- What is an AI Agent? (Explained Simply)
- Why Do We Need Agent Design Patterns?
AI & Automation
115 free guides
LLMs, RAG, prompt engineering, and AI app architecture for the new AI engineering interview round.
- A2A Protocol
- AI Agents Intro
- AI App Architecture
- AI Chatbots
- AI Coding Tools Deep Dive (Cursor, Claude Code, Copilot)
- AI Music & Audio Generation (Suno, Udio)
- AI Regulations & Compliance (EU AI Act, SOC2)
- AI Resume
Show all 115 guides
- AI Safety, Ethics & Responsible AI
- AI System Design Interview Prep
- AI Video Generation (Sora, Runway, Kling)
- AI/LLM Interview Questions & Answers
- AI/ML Overview & Key Concepts
- API Cost & Rate Limit Management
- AWS Bedrock & Azure OpenAI
- Advanced RAG
- Agent Evaluation
- Agent Memory
- Agent Observability
- Agent Orchestration Patterns (Sequential, Parallel, Hierarchical)
- Agentic Prompting (Planning, Reflection, Tool Use)
- Agents with MCP Tools & Servers
- Agno Framework (Fast Multi-modal Agents)
- Anthropic API
- Audio AI
- BM25 & Hybrid Search (Sparse + Dense Retrieval)
- Building Custom MCP Servers & Tools
- Building MCP Servers
- CAMEL Framework (Multi-Agent Collaboration)
- CI/CD for AI Applications
- Chainlit (ChatGPT-like UI for AI Apps)
- Chat UI Patterns & Best Practices
- Chunking Strategies (Recursive, Semantic, Agentic)
- Claude Agent SDK (Anthropic)
- Cloud Deployment (AWS, GCP, Fly.io, Railway)
- Computer Use
- Context Windows, Parameters & Model Sizes
- DSPy (Programming, not Prompting LLMs)
- Docker for AI (Containerizing AI Apps)
- Document AI (Invoice, Receipt, Form Extraction)
- Document Parsing (Unstructured, Docling, PyPDF)
- Domain-Specific Prompting (Code, Legal, Medical)
- Embedding Selection
- Embeddings & Similarity Search
- FastAPI for AI Backends (Streaming, WebSockets)
- Few-Shot & CoT
- Fine-tuning LLMs (LoRA, QLoRA, RLHF, DPO)
- GPT vs Claude vs Gemini vs LLaMA vs Mistral
- Git, CLI & Developer Tooling
- Google ADK (Agent Development Kit)
- Google AI API (Gemini, Vertex AI)
- Gradio
- Guardrails
- HTTP, REST APIs & Web Fundamentals
- Haystack (End-to-end RAG Framework)
- How LLMs Work
- Hugging Face & Open Source Models
- Image Generation (DALL-E, Midjourney, Stable Diffusion)
- Inference Optimization (Quantization, Batching, KV Cache)
- Instructor (Pydantic-based Structured Output)
- JSON & YAML
- Jupyter & Colab
- Key AI Research Papers (Must-Read)
- Knowledge Graphs
- LLM Cost Management & Token Optimization
- LLM Observability Stack (LangFuse, Arize, Helicone)
- LLMOps & Model Lifecycle Management
- LangChain
- LangGraph
- LangSmith (Tracing, Debugging & Evaluation)
- LiteLLM & OpenRouter (Universal LLM Gateway)
- LlamaIndex (Data Agents & Query Engines)
- MCP Protocol (Model Context Protocol Spec)
- Markdown & Technical Writing
- Mastering Claude Code (Skills, Hooks, MCP & AI Teams)
- Meta-Prompting & Prompt Chaining
- Model Benchmarks & Evaluation (MMLU, HumanEval)
- Multi-Agent Systems (CrewAI, AutoGen, Swarm)
- Multimodal RAG (Images, Tables, PDFs)
- Next.js + Vercel AI SDK (Full-stack AI Apps)
- No-Code AI Platforms (Flowise, Langflow, Dify)
- Open WebUI & Self-hosted Chat Interfaces
- OpenAI API
- OpenAI Agents SDK
- Portfolio Project: AI-Powered SaaS App
- Portfolio Project: Multi-Agent Workflow System
- Portfolio Project: RAG Chatbot with Citations
- Prompt Basics
- Prompt Evaluation (Promptfoo, DeepEval, RAGAS)
- Prompt Patterns (ReAct, ToT, Self-Refine)
- Prompt Security & Red Teaming (Injection, Jailbreaks)
- Prompt Templates
- Pydantic AI (Type-safe AI Agents)
- Python Async
- Python Environment Setup (venv, pip, poetry)
- RAG Architecture & Pipeline Design
- RAG Evaluation (RAGAS, Faithfulness, Relevancy)
- ReAct Pattern Deep Dive (Reasoning + Acting)
- Running Local LLMs (Ollama, vLLM, llama.cpp)
- Scaling Laws & Emergent Abilities
- Semantic Kernel (Microsoft AI Framework)
- Sentence Transformers
- Smolagents (HuggingFace Lightweight Agents)
- Streamlit
- Structured Output
- System Prompts
- Tokenization
- Tool Use
- Transformer Deep Dive
- Vector DB Comparison & Selection Guide
- Vector Databases (Pinecone, Weaviate, ChromaDB, Qdrant)
- Vercel AI SDK & Streaming Interfaces
- Vision AI
- Voice AI (ElevenLabs, TTS, Realtime Voice)
- Workflow Automation (n8n, Zapier, Make)
Practice these topics on DevInterviewMaster
Every guide here has an interactive version — animated explainers, quizzes, and Hinglish notes.
800+ system-design, LLD, coding, and design-pattern topics. Unlock everything with Pro (₹499, one-time) or Ultimate (₹999, one-time) — lifetime access, no subscription.