Start with Foundations if you’re new — build an agent by hand, no framework. Move to Production once the basics click. Pick by where you are right now.

1Level 1Foundations — build it by hand

2Level 2Production — ship a real one

★ Start here

01Beginner · Foundations

AI Agents from Scratch in Python

Build a working agent with nothing but Python and one LLM call — no frameworks, so you actually understand the loop.

Start here if you…

are new to agents, or want to know how one actually works before reaching for a framework.

Length: 6 parts (00–05)
Approach: Pure Python + a raw LLM call
Prereq: Can read basic Python (Part 0 teaches it)
You'll build: Your own agent loop — tools, reasoning, memory — by hand

Start Part 00 — Python basics →

02Intermediate · Production

Agentic AI in Python: Zero to Production

Take a real agent all the way to a deployed, observable service using LangGraph — state, tools, memory, and shipping.

Start here if you…

already get the basics (or finished Level 1) and want to ship something production-grade.

Length: 7 parts (01–07)
Approach: LangGraph + deploy & observability
Prereq: Comfortable with agent fundamentals
You'll build: A real agentic app, deployed as an observable service

Start Part 01 — first build →

AI Engineering · flagship

Build it, in real Python

All 76 guides →

Guide · 5 minChatGPT MCP: Connect Any MCP Server to ChatGPT (2026)ChatGPT MCP setup in 2026: turn on Developer Mode, add your MCP server as a custom connector over OAuth, and handle the write-confirmation gotcha.Sukhveer Kaur · Oct 14, 2026

Opinion · 4 minClaude 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.Sukhveer Kaur · Aug 1, 2026

Guide · 8 minEvaluate 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.Sukhveer Kaur · Jul 18, 2026

Guide · 9 minAI 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.Sukhveer Kaur · Jul 6, 2026

Guide · 5 minBuild 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.Sukhveer Kaur · Jul 4, 2026

Guide · 4 minLLM 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.Sukhveer Kaur · Jul 4, 2026

AI Tools & Reviews

Tools worth your time

All 5 guides →

Review · 7 minOpenRouter 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.Sukhveer Kaur · Jul 3, 2026

Guide · 5 minBest 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.Sukhveer Kaur · Jun 28, 2026

Review · 5 minn8n 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.Sukhveer Kaur · Jun 27, 2026

Software Architecture

Design systems that hold up

All 26 guides →

Guide · 11 minDesign a URL Shortener: Where Every Decision Comes From the Read Path (2026)Design a URL shortener for a system design interview: requirements, base62 short codes, caching a 100:1 read path, 301 vs 302 and abuse checks.Sukhveer Kaur · Oct 19, 2026

Guide · 8 minUpdated 20 OctBack-of-Envelope Estimation for System Design Interviews: The Maths in 30 Seconds (2026)Back-of-envelope estimation for system design interviews: five numbers, four formulas, 2026 latency figures and how to size an AI feature in under a minute.Sukhveer Kaur · Oct 17, 2026

Guide · 8 minSystem Design Interview Framework: Six Steps for the 45-Minute Round (2026)A system design interview framework for 2026: six steps, a time box for each in the 45-minute round, and what the interviewer scores at each step.Sukhveer Kaur · Oct 16, 2026

Tech Career Growth

Grow in the AI era

All 16 guides →

01AI Agent Interview Questions (2026): Strong vs Weak Answers11 min 02AI Engineer Behavioral Interview (2026): Present the Project You Built7 min 03The AI Engineer Interview Prep Plan (2026): 2 to 4 Weeks6 min 04AI Engineering Portfolio Projects That Get Interviews (2026)6 min 05LLM Evaluation Interview Questions (2026): Strong vs Weak Answers9 min 06LLM System Design Interview: The Five-Layer Answer (2026)11 min

New AI engineering guides, the day they ship

Real Python, production depth — straight to your inbox. No digest spam, unsubscribe anytime.