Category archive

engineering

Explore 13 articles grouped under this category so it's easier to browse a broader theme instead of a single keyword.

13 of 75 published postsBest for exploring one broader area end to end

Best place to start

More in this category

Keep exploring

engineeringApr 19, 202613 min read

The AI Code Security Field Guide: 10 Vulnerabilities You're Shipping Right Now

AI-generated code looks clean and ships fast — and quietly introduces a predictable set of security holes. Here's an OWASP-style guide to the most common AI code vulnerabilities in 2026, with real examples and fixes.

#security#ai-coding#owasp+2 more
Read article
engineeringApr 19, 202614 min read

How to Build AI Agents for Business Automation: A Builder's Guide

The technical playbook — architecture, tool design, eval, deployment, and monitoring. Everything you need to ship an agent that survives contact with real users in 2026.

#build-agents#architecture#tool-design+2 more
Read article
engineeringApr 19, 202610 min read

Why Infinite Canvas Beats A/B Testing for AI Work

A/B testing assumes you know the two options worth testing. With AI, the bigger win comes from generating twenty options on a canvas and picking by eye. Here is why and when.

#product-design#ab-testing#ai-workflow+2 more
Read article
engineeringApr 19, 202613 min read

Multi-Agent Orchestration: Patterns, Frameworks, and What Actually Works in 2026

Orchestrator-worker, swarm, supervisor, hierarchical — the real patterns behind multi-agent systems, with honest takes on LangGraph, CrewAI, AutoGen, and when to skip them entirely.

#multi-agent#orchestration#langgraph+2 more
Read article
engineeringApr 19, 202611 min read

Multi-Framework AI Generation: One Spec, Four Frontends

Generating the same UI component across React, Vue, Svelte, and Solid with AI in 2026 — why it matters, when it actually works, and the prompt pattern that makes it usable in production.

#ai-coding#frameworks#react+3 more
Read article
engineeringApr 19, 202613 min read

I Rebuilt My RAG System Three Times. Here's What I Wish I'd Known.

A first-person account of building, breaking, and rebuilding the same RAG system three times in 18 months. The lessons that only show up after you've shipped it twice and regretted it.

#rag#lessons-learned#retrieval+2 more
Read article
engineeringApr 19, 202612 min read

The Vibe Coding Revolution: How a Joke Tweet Rewired the Developer Job

Vibe coding started as a Karpathy throwaway and ended as a labor restructuring. Here's the cultural and industry essay — what the developer role actually became, who won, who lost, and what's next.

#vibe-coding#developer-culture#industry+2 more
Read article
engineeringApr 19, 202612 min read

Why Your RAG Chatbot Sucks (And How to Fix It)

Most production RAG chatbots are bad in predictable ways. Here are the real reasons — chunking, retrieval, eval, prompting — and the fixes that actually move the needle in 2026.

#rag#retrieval#chunking+2 more
Read article
engineeringApr 3, 202611 min read

How AI Agents Actually Work: Tool Use, Memory, and Orchestration Explained

'Agentic AI' is the buzzword of 2026 — but what's actually happening under the hood when an agent books your flight, refactors your code, or runs a 5-step research task? A plain-English breakdown with real examples.

#ai-agents#agentic-ai#tool-use+2 more
Read article
engineeringMar 27, 202611 min read

MCP (Model Context Protocol) Explained: The 'USB-C for AI Agents'

MCP is the plug standard that lets any AI model connect to any data source or tool — Gmail, GitHub, Notion, your filesystem — without bespoke integrations. Here's what it is, why it won, and how to actually use it in 2026.

#mcp#ai-agents#model-context-protocol+2 more
Read article
engineeringMar 20, 202610 min read

Multi-Model AI Workflows: Routing Prompts to the Right Model Automatically

Using one AI model for everything is like using one screwdriver for every job. Here's how to route each task to the best-fitting model — cheap for bulk, expensive for hard, fast for interactive — and cut your AI bill by 60% without losing quality.

#multi-model#ai-workflow#cost-optimization+2 more
Read article
engineeringMar 3, 202611 min read

RAG vs Fine-Tuning vs Long Context: When to Use Each in 2026

Stop picking RAG by default. With 2M-token context windows, 90% prompt cache discounts, and cheap fine-tuning, the right choice for 'teach my AI about my data' has changed. Here's the real decision framework.

#rag#fine-tuning#long-context+2 more
Read article