Categories

AI Engineering AI Tools & Reviews Software Architecture Tech Career Growth

Home Guides Authors About Contact

// author

Sukhveer Kaur

Sukhveer is a software developer specialising in AI systems and backend engineering. She has hands-on experience designing agentic AI applications, working with large language model pipelines, autonomous agent frameworks, and cloud-native services in Java and Python. At InfoWok, she bridges the gap between cutting-edge AI research and practical implementation — helping developers understand and apply emerging technologies through clear, experience-backed writing.

88 guides~8.6 hrs totalupdated Aug 1, 2026

 Start here

Claude Code Skills Tutorial: Build Your First Skill (2026)

Claude Code Skills turn a repeated prompt into a folder Claude reaches for on its own. Build one real Skill and run it in this hands-on tutorial.

Beginner · 7 min

AI Engineering

Read the guide →

All guides

88 on this page

IntermediateClaude Code Changes 2026: Subagent Limits, Caps & Opus 5Claude Code changes shipped fast: subagent limits flip-flopped twice, a budget-cap bug got fixed, and Opus 5 became the default. Here is what to do.4 min BeginnerEvaluate an AI Agent on a Local LLM: Free, No API Key (2026)Evaluate an AI agent on a local LLM for free — build a tiny Pydantic AI agent on Ollama and score it with pydantic-evals, agent and judge both local, no API key.8 min IntermediateAI Agent Guardrails in Python: Input & Output ValidationAI agent guardrails in Python: validate input and output, block prompt injection, and enforce schemas with the OpenAI Agents SDK and Pydantic.9 min IntermediateAgentic Search vs RAG: Which One Do You Actually Need? (2026)Agentic search vs RAG, decided: a flowchart, real cost data, and the default that wins most of the time — plus exactly when to pay for the upgrade.6 min IntermediateMCP Server TypeScript: Build One in Node.js (2026)Build an MCP server TypeScript developers can deploy — typed tools with Zod, Streamable HTTP in Node.js, and a curl test that proves it works.6 min IntermediatePydantic AI vs LangChain: Which Framework Should You Use? (2026)Pydantic AI vs LangChain in 2026: real code for both, a clear verdict on which to pick, and exactly where each framework stands right now — including the v2 beta.6 min Designing AI-Native Applications: The Architecture SeriesAI-native applications break classic architecture instincts. This 8-part series maps the decisions that matter: context, memory, orchestration, governance.3 min BeginnerBest Local LLM for Your Laptop in 2026: Free and PrivateFind the best local LLM for your laptop — matched to 8, 16 or 32 GB of RAM — and run it free with LM Studio or Ollama. No API bills, fully private.7 min BeginnerClaude Code MCP with Local Models: A Private Agent StackClaude Code MCP on a free local stack: add servers with one command, pick tool-capable Ollama models, set scopes right, and dodge the privacy trap.5 min BeginnerConnect Claude Code to Any Model: 6 Exact Configs (2026)Connect Claude Code to Ollama, DeepSeek, GLM, Kimi, NVIDIA NIM or OpenRouter: copy-paste env vars, settings.json blocks, model mapping and quick fixes.5 min BeginnerFree Local AI Coding Assistant in VS Code (2026 Setup)Set up a free local AI coding assistant in VS Code with Continue and Ollama: the right Qwen coder models for your RAM, plus chat, edits and autocomplete.5 min BeginnerLocal RAG: Chat With Your Documents 100% Privately (2026)Set up local RAG and chat with your documents fully offline: Open WebUI knowledge bases for the no-code path, plus a tiny Python pipeline with Ollama.5 min BeginnerRun Claude Code for Free: What Viral Videos Don't Tell YouThose viral videos about running Claude Code for free are half true. What is actually free, what costs money, and three real setups that work in 2026.6 min IntermediateSoftware Engineer Skills in 2026: What the Job Now ExpectsThe software engineer skills that get you hired changed in 2026: AI-assisted coding, LLM integration, agent literacy — plus a 6-point self-audit.5 min IntermediateBuild a Customer Support AI Agent in Python (2026)Build a customer support AI agent in Python with the OpenAI Agents SDK: triage, order lookup, refunds, human escalation, and memory — with runnable 2026 code.5 min IntermediateLLM Structured Outputs: Validated JSON in Python (2026)Get structured outputs from LLMs in Python: validated JSON, not fragile parsing — with Pydantic, OpenAI Structured Outputs, and instructor. Runnable code.4 min IntermediateOpenAI Agents SDK Handoffs: Multi-Agent Routing in PythonMaster OpenAI Agents SDK handoffs in Python: route between specialist agents, customize with handoff(), pass data with input_type, and filter history.5 min IntermediateOpenAI Agents SDK Tutorial: Build an Agent in Python (2026)Build your first AI agent with the OpenAI Agents SDK in Python: tools, structured output, handoffs, and memory — with runnable 2026 code and common pitfalls.6 min IntermediateOpenAI Agents SDK vs LangGraph: Which to Use in 2026?OpenAI Agents SDK vs LangGraph in 2026: a managed agent loop or an explicit state graph? A head-to-head on control, state, durability, and when to pick each.5 min BeginnerOpenRouter Review (2026): One API, 300+ Models — Worth It?OpenRouter review (2026): one API for 300+ LLMs with automatic failover and zero markup — but a 5.5% credit fee. Real costs, limits, and who should use it.7 min IntermediateVector Database for RAG: When to Ditch the List (Part 4)A vector database for RAG earns its place when persistence, filters, or scale demand it — move the Part 1 list store to Chroma and add hybrid search.7 min IntermediateSemantic Chunking & Re-Ranking for Better RAG (Part 3)Semantic chunking and cross-encoder re-ranking break the retrieval ceiling fixed-size chunks hit — with a hit-rate eval showing which to reach for first.6 min IntermediateRAGFlow: Fix Bad RAG Retrieval on Real PDFs (2026)RAGFlow fixes the RAG failure you can't out-prompt — bad PDF and table parsing. See how its deep document understanding reads tables right, and when to use it.5 min BeginnerPython Environment Setup for AI Agents: The 5-Minute Primer (2026)The one setup every AI agent tutorial assumes: install Python, create a virtual environment, install packages, and add your API key with a .env file — in about five minutes.4 min IntermediateAgentic RAG: Why Static Retrieval Isn't Enough (2026)Agentic RAG wraps retrieval in an agent loop that grades its own results and re-queries when they're weak. Here's how it beats static RAG — and what it costs.6 min IntermediateBuild a RAG System in Python From Scratch (Part 1)Build a RAG system in Python from scratch — no framework. Four functions that chunk, embed, store, and retrieve over your own docs, then answer with an LLM.8 min IntermediateRAG Chunking & Retrieval Quality: Fix Bad Answers (Part 2)Fix RAG chunking to stop wrong answers — use fixed-size windows, overlap, and a 10-line retrieval eval. The model was never the problem; the chunks were.6 min BeginnerBest n8n Alternatives for AI Agents (2026)The best n8n alternatives for AI agents in 2026 — Make, Activepieces, Zapier, Gumloop, Lindy, Relevance AI and Pipedream, with honest picks by use case.5 min Beginnern8n Review (2026): Best No-Code AI Agent Builder?n8n review (2026): the most capable low-code platform for building real AI agents — native agent nodes and per-execution pricing, but a steep learning curve.5 min BeginnerCursor vs Claude Code (2026): Which Should You Use?Cursor vs Claude Code in 2026: editor AI vs terminal agent, pricing, token efficiency, and which to use — or why many developers run both.7 min IntermediateAI Engineer Interview Questions (2026): RAG & AgentsA 2026 playbook of AI engineer interview questions by round: RAG, agents, LLM system design, and evals, with what each really tests and how to answer.5 min IntermediateBecome an AI Engineer: The 80% You Already Know (2026)You already do 80% of an AI engineer's job. If you ship software, here's the exact 20% you need to become an AI engineer in 2026: RAG, agents, evals.6 min IntermediateHow to Evaluate an AI Agent: Metrics & Frameworks (2026)An AI agent evaluation guide for 2026: the metrics that actually matter, how to score them, and the frameworks — LangSmith, DeepEval, Ragas — to run them.9 min IntermediateWhy Your LangGraph Agent Keeps Looping (and How to Fix It)Your LangGraph agent looping until GraphRecursionError? Here's how to diagnose the four causes and fix the stop condition — not just raise the limit.9 min Beginnern8n vs Make for AI Agents (2026): Which to Usen8n vs Make for AI agents in 2026: how their agent nodes, pricing (executions vs credits), and setup differ — and which one to actually pick.7 min BeginnerPydantic BaseModel: A Primer for AI Agent Developers (2026)A Pydantic BaseModel primer for AI agent developers: define a model, validate data, and turn messy LLM output into a clean, typed Python object.4 min BeginnerWhat Is RAG in AI? A Practical Developer's Guide (2026)What is RAG? A developer's guide to retrieval-augmented generation: why LLMs need it, the retrieve-augment-generate loop, and a runnable RAG in 25 lines.6 min BeginnerPython Decorators: A Primer for Reading AI Agent Code (2026)A Python decorators primer for reading AI agent code: what the @ symbol does, how @tool and @app.get work, and why frameworks hand you decorators to apply.4 min BeginnerAI Agent vs Workflow: What's the Actual Difference? (2026)AI agent vs workflow, settled: one question tells you which you actually have. The difference is who decides the next step — your code, or the model — with code examples.5 min BeginnerAsync and Await in Python: A Primer for AI Agent Code (2026)An async and await in Python primer for reading AI agent code: what async def, await, and asyncio.run mean, and the two mistakes beginners always hit.5 min BeginnerDocker for Python: A Primer for Shipping AI Agents (2026)A Docker for Python primer: what images and containers are, how to write a Dockerfile for an app, and why agents ship in containers — explained simply.4 min BeginnerEmbeddings and Vector Search: A Primer for AI Agents (2026)An embeddings and vector search primer: how text becomes vectors, how similarity search finds meaning not keywords, and why agent memory and RAG rely on it.4 min BeginnerHTTP and Bearer Tokens: A Primer for Python Devs (2026)An HTTP and bearer token primer for Python devs: methods, status codes, JSON bodies, and how an Authorization Bearer header authenticates an API call.5 min BeginnerLLM API Keys: Set Up OpenAI, Anthropic & Gemini (2026)An LLM API key primer: where to get OpenAI, Anthropic, and Gemini keys, how to load one safely with python-dotenv, and how to avoid a leaked-key bill.4 min BeginnerOAuth 2.1 in Plain English: A Primer for Developers (2026)An OAuth 2.1 primer in plain English: access tokens, scopes, the client–server–authorization flow, and how it protects an API or MCP server from anyone.4 min BeginnerPytest and CI: A Primer for Testing AI Agents (2026)A pytest and CI primer: write a first test, run it, and wire it into GitHub Actions so every pull request is checked automatically — explained for beginners.4 min BeginnerPython Type Hints: A Primer for Reading AI Agent Code (2026)A Python type hints primer for reading AI agent code: function hints, Optional, Union, TypedDict for message lists, and how frameworks use them.5 min BeginnerPython Virtual Environments: venv, pip & uv Primer (2026)A Python virtual environment primer: why venv exists, how to create and activate one, install packages with pip or uv, and avoid the classic setup traps.4 min BeginnerWhich AI Agent Framework Should You Use in 2026?A developer's decision guide to the best AI agent frameworks in 2026 — three questions to confidently pick LangGraph, CrewAI, the OpenAI or Claude SDK.9 min IntermediateAgentic AI in Python: Zero to Production — The Full SeriesThe complete Agentic AI in Python series — six parts that take you from a local LangGraph agent to a deployed, memory-keeping, tool-using, observable app. Start here.1 min BeginnerFrom Scratch to LangGraph: When to Stop Hand-Building AgentsFrom scratch to LangGraph: the four walls that tell you when to use LangGraph instead of a hand-built Python agent loop — and when plain Python is still the right call.5 min IntermediateAI Agent Evals in CI: Block Bad PRs with GitHub ActionsRun AI agent evals in CI: turn your pydantic-evals suite into a test, gate it with GitHub Actions, and block any pull request that drops the agent's score.6 min IntermediateGoogle ADK Tutorial: Build Your First AI Agent in Python (2026)A Google ADK tutorial that fills the setup gap most tutorials skip: go from an empty folder to a running AI agent in Python, with a validation loop and an MCP connection.7 min IntermediateLangGraph Tutorial: Build Your First AI Agent in Python (2026)A LangGraph tutorial for 2026: build your first AI agent in Python with create_agent, then rebuild it as a raw StateGraph so you actually see what's underneath.7 min BeginnerAI Agent Loop in Python: Build a ReAct Agent From ScratchBuild an AI agent loop in Python from scratch: a framework-free ReAct agent that thinks, calls a tool, observes the result, and repeats until the job is done.7 min BeginnerAI Agent Memory in Python: Short-Term Memory From ScratchAdd AI agent memory in Python from scratch: keep the conversation in a messages list, then trim and summarize older turns to fit the model's context window.7 min IntermediateCrewAI Tutorial: Build a Multi-Agent Team in Python (2026)CrewAI tutorial: build a 3-agent team in Python — researcher, writer, and editor — with runnable 2026 code, and exactly when a crew is overkill.7 min Beginnern8n AI Agent Tutorial: Build One Without Code (2026)Build an n8n AI agent without code: wire four nodes into a working agent, see each node mapped to the loop underneath, and learn when to switch to Python.6 min BeginnerPython for AI Agents: The Basics to Read the Code (Part 0)The Python for AI agents you actually need to read the code: dicts, functions, type hints, loops, async, and setup — explained simply for beginners.6 min BeginnerCall an LLM in Python: The First Building Block of an AgentCall an LLM in Python with real OpenAI and Anthropic code: system vs user prompts, temperature, JSON output, and why one call isn't yet an agent.6 min BeginnerTool Calling in Python: Make an LLM Use Your FunctionsTool calling in Python from scratch: define a tool, parse the model's request, run your function, and return the result — with real, current OpenAI code.7 min 7 Best MCP Servers to Connect to Claude in 2026The 7 best MCP servers to connect to Claude in 2026 — what each one does, when to actually use it, and the one permission to check before you connect.6 min IntermediateAI Agent Observability & Evals in Python (Part 6)Add AI agent observability and evals in Python — trace every agent run with Pydantic Logfire and score it against a test set using pydantic-evals.7 min MCP vs A2A: Do Your AI Agents Need Both? (2026)MCP vs A2A in 2026, in plain English: MCP connects an agent to tools, A2A connects agents to each other. Here's when you need both — and when you don't.5 min MCP vs REST API: Do You Even Need MCP? (2026)MCP vs REST API in plain English: a REST call connects your code to a tool, MCP connects any AI agent to it. Here's when you actually need MCP.5 min Are MCP Servers Safe? Security Risks & How to Lock Them DownAre MCP servers safe? Here's what one can really access, the real risks — tool poisoning, no-auth endpoints — and a five-minute hardening checklist.5 min IntermediateBuild an Agentic AI App in Python: MCP Client (Part 5)Build an MCP client in Python so your agent calls real tools — connect a LangGraph agent to an authenticated FastMCP server with langchain-mcp-adapters.7 min IntermediateGitHub MCP Server: Connect Claude to Your Repos (2026)Connect the GitHub MCP Server to Claude in 15 minutes — the exact Docker config, a least-privilege token, the 6 things it does well, and the scope you must not skip.7 min BeginnerAgentic AI Roadmap 2026: Worth It + the Exact PathAn honest agentic AI roadmap for 2026: is it worth learning, the exact path from Python to a deployed agent, what to skip, and the tools that matter.5 min BeginnerClaude MCP Setup: Connect a Server to Claude Desktop (2026)Edited your Claude MCP config but nothing shows up in Claude Desktop? Get the exact claude_desktop_config.json for macOS and Windows, plus every fix.6 min IntermediateLangGraph vs CrewAI vs AutoGen: Which to Use in 2026?LangGraph vs CrewAI vs AutoGen compared for 2026: dev speed, production reliability, observability, and how to pick the right Python AI agent framework.6 min IntermediatePydantic AI Tutorial: Type-Safe AI Agents in Python (2026)Pydantic AI tutorial: build type-safe AI agents in Python with structured outputs, tools, dependency injection and native MCP, plus runnable 2026 code.8 min BeginnerWhat Is an MCP Server? Complete Guide for Developers (2026)What is an MCP server? A plain-English 2026 guide to the Model Context Protocol: how MCP servers work, MCP vs APIs, and whether to adopt one.5 min IntermediateBuild an Agentic AI App in Python: AI Agent Memory (Part 4)Add real AI agent memory in Python — a LangGraph Store that recalls users across threads, semantic search with embeddings, and Redis for production.7 min IntermediateBuild an Agentic AI App in Python: Multi-Agent Systems (Part 3)Build multi-agent systems in Python with LangGraph: a supervisor routing search, summarise & fact-check workers, plus loop guards that save real money.8 min IntermediateBuild an MCP Server in Python: Production-Ready in 2026Build a production-ready MCP server in Python with FastMCP — typed tools, OAuth 2.1 auth and streamable-HTTP deployment that most 2026 tutorials skip.7 min IntermediateDeploy AI Agent to Cloud Run or Fly.io (Python 2026)Deploy AI agent code to Cloud Run or Fly.io in one command: push once, get a live HTTPS URL, and keep your Postgres-backed agent memory intact — no VPS.8 min IntermediateBuild an Agentic AI App in Python: FastAPI, Docker & Deploy to Production (Part 2)Wrap your LangGraph agent in FastAPI, Dockerize it, and deploy to a cloud VPS. Part 2 of the Agentic AI Python series — zero to production.9 min IntermediateHow to Crack a Google Interview in India (2026 Guide)A step-by-step 2026 guide to cracking a Google interview in India — the real rounds, DSA and system design prep, Googliness, and a week-by-week plan.6 min IntermediateBuild an Agentic AI App in Python: Zero to Production (Part 1)Learn how to build a working agentic AI app in Python with LangGraph. Part 1 covers tools, StateGraph, and memory — step by step from scratch.9 min BeginnerWhat Are AI Agents? Complete Guide for Developers (2026)Learn what AI agents are, how they work, and when to use them. A practical developer's guide covering LLMs, tool use, memory, and real-world examples in 2026.6 min Google Interview Prep Beyond Coding: PM, Sales & GooglinessPrepare for a Google interview beyond the code — PM, sales and marketing roles, the Googliness rubric, STAR stories, and the mindset that wins offers.4 min BeginnerFull Stack Developer Training in 2026: Courses + PathA practical guide to full stack developer training in 2026: the best courses compared, the exact learning path, India salary data, and how to pick one.5 min BeginnerThe Future of Work: A Deep Dive into the Digital RevolutionThe future of work in 2026: AI agents as coworkers, hybrid as the default, and a looming skills cliff. The real data, the trends, and how to stay ahead.4 min BeginnerDeepfakes in 2026: Real Risks and How to Spot ThemWhat deepfakes are in 2026, the real fraud risks, how to spot deepfakes and verify media, the detection tech (C2PA, SynthID), and the new laws.5 min Beginner5 Top React UI Libraries for Modern Web Apps (2026)A 2026 guide to the top React UI libraries — MUI, Ant Design, shadcn/ui, Mantine and Chakra UI — with honest trade-offs and how to pick the right one.7 min BeginnerNavigating the AI Learning Revolution in 2026: From Hype to Hands-OnHow to learn AI in 2026: a practical, hands-on path from hype to real skills — no-code tools, microlearning, building projects, and working with AI.5 min

Following Sukhveer Kaur?

Get new Sukhveer Kaur guides the day they publish. One email, no spam.