Jul 2026 • Tech, System Design

Design Uber / a Ride-Hailing System - System Design

“Design Uber” sounds like a CRUD app with a map on top. A rider taps a pin, a driver shows up, money moves. The interviewer lets you believe …

Read More
Jul 2026 • Tech

Spec-Driven Development - Writing the Spec Is Writing the Code Now

The most productive engineers I know stopped bragging about how fast they type. When a coding agent can produce 400 lines of correct code …

Read More
Jun 2026 • Tech

Choosing an Embedding Model in 2026 - It's Not the Leaderboard

Most teams pick an embedding model the same way they pick a sorting algorithm: look up the benchmark, take the top result, ship it. For …

Read More
Jun 2026 • Tech, System Design

Design a URL Shortener (TinyURL) - System Design

Everyone thinks the URL shortener is a trivial problem. “It’s a hash map. Store long URL, return short URL, done.” Then the interviewer …

Read More
Jun 2026 • Tech, System Design

Design Twitter's News Feed - System Design

The Twitter timeline looks trivial until you say the numbers out loud. “Show me a list of tweets from people I follow, newest first.” It is …

Read More
Jun 2026 • Tech, System Design

Design WhatsApp / a Chat Messaging System - System Design

A chat app sounds like the easiest system you will ever build. “User A sends a message, user B receives it.” One INSERT, one SELECT. The …

Read More
Jun 2026 • Tech

Multi-Agent Systems - When Splitting the Work Actually Helps

The instinct when a task is complex is to throw more agents at it. Spin up a researcher, a writer, a critic, a planner - a whole crew. It …

Read More
Jun 2026 • Tech

Observability for LLM Apps - You Can't Fix What You Can't Trace

When your web service throws a 500, you have a stack trace. When your LLM app returns a bad answer, the status code is 200, the latency …

Read More
Jun 2026 • Tech

Semantic Caching - The Cheapest 40% Off Your LLM Bill

The cheapest optimization most teams skip is not routing to smaller models or trimming the context window. It is not calling the model at …

Read More
Jun 2026 • Tech

Structured Outputs - Stop Parsing LLM JSON by Hand

If you have a regex somewhere that strips markdown fences to pull JSON out of an LLM response, you have a time bomb. It works 95% of the …

Read More
Jun 2026 • Tech

Context Engineering - The Discipline That Replaced Prompt Engineering

The question engineers ask most often when an LLM pipeline underperforms is: “how should I reword this prompt?” That is almost never the …

Read More
Jun 2026 • Tech

Small Language Models Are Eating the Easy 80%

Most production AI costs are paid to frontier models for tasks that a 3-billion-parameter model running locally could handle just as well. …

Read More
Jun 2026 • Tech

Diffusion LLMs - The Text Models That Don't Predict Left to Right

Every LLM you have used in production generates text the same way: one token at a time, left to right, each token depending on everything …

Read More
Jun 2026 • Tech

What 'Thinking' Actually Costs - Reasoning Models and Test-Time Compute

When you enable extended thinking on Claude or switch to an o-series model, the price per request jumps 3 to 10x. That is not because you …

Read More
Jun 2026 • Tech

Your AI Agent Is a Security Hole - Prompt Injection in 2026

Most engineers building agents spend time worrying about hallucinations. The more immediate risk is that your agent will faithfully execute …

Read More
Jun 2026 • Tech

You're Shipping AI Features Blind - Eval-Driven Development in 2026

The dirty secret of most AI product teams in 2026: when someone asks “how do you know the new prompt is better?” the honest answer is “we …

Read More
Jun 2026 • Tech

How AI Agents Actually Remember - Memory Architectures in 2026

Ask anyone building agents what their biggest problem is and “memory” comes up within the first two sentences. The agent solved the bug …

Read More
Mar 2026 • Tech

AI-First Development Is Not Vibe Coding - Here Is the Difference in 2026

The term “vibe coding” entered the vocabulary in early 2025. The idea: describe what you want, let the AI write it, accept the output, …

Read More
Mar 2026 • Tech

Building AI Agents That Actually Work in Production in 2026

Every AI framework promises agents that can “autonomously complete complex tasks.” The demo shows an agent booking flights, writing code, …

Read More
Mar 2026 • Tech

Building Custom Skills for Claude Code - The No-Code Way to Extend AI in 2026

Claude Code has a plugin system that requires no code. Skills are markdown files that live in ~/.claude/skills/ and define reusable …

Read More