Research & Insights

What we're thinking about

Technical writing, architecture decisions, and honest assessments of AI tooling from engineers who build with it daily.

152 articles published

Featured

Tools

Cursor vs Claude Code in April 2026: What Actually Changed

Our original Cursor vs Claude Code comparison got valid pushback — Cursor has shipped agent mode, subagents, a CLI, cloud agents, and terminal access since we wrote it. Here is the corrected picture as of April 2026, with what actually matters for choosing between them now.

Read articleApr 8, 2026 · 8 min read

152 articlesLatest first

APR142026

AI News4

Linux Just Settled Its AI Code Debate — Here's What It Actually Means

The Linux kernel team just formalized its AI coding policy. Copilot and Claude Code are allowed — but every line you submit is yours to own. Here is what it means for every engineering team that hasn't figured this out yet.

APR132026

Opinion12

AI Benchmarks Are Broken and Nobody Wants to Admit It

SWE-bench scores keep climbing, marketing decks keep citing them, and production AI keeps disappointing. After 14 years of watching the software industry worship vanity metrics, I am calling it: AI benchmarks measure benchmark performance, not real-world capability.

APR132026

Engineering12

How to Add Streaming AI to Your Next.js App Without a Surprise API Bill

A step-by-step guide to building streaming AI features in Next.js with the Vercel AI SDK — including the token limits, error boundaries, and cost controls that tutorials skip.

APR132026

Tools6

ROCm vs CUDA in 2026: After Testing Both, Here's the Truth

AMD's ROCm is finally a real CUDA alternative in 2026. But "real alternative" and "drop-in replacement" are very different claims. Here's what actually works, what doesn't, and who should switch.

APR132026

AI & Engineering14 min read

The State of AI Agent Frameworks in 2026

The agent framework landscape consolidated fast in 2025. LangGraph, AutoGen, and CrewAI each won different segments — here is what actually separates them and how to pick for your use case.

APR122026

Explainer5

Agentic Coding Explained for People Who Don't Write Code

Your engineering team is talking about AI agents that write code autonomously. Here is what that actually means for your product timeline, your budget, and the questions you should be asking before you sign off on it.

APR122026

Engineering13 min read

The CI/CD Pipeline That Actually Works in 2026

GitHub Actions became the default. Blacksmith made it faster. Multi-stage Docker builds became standard practice. AI entered the pipeline. This is what a well-engineered CI/CD setup looks like going into the second half of 2026.

APR122026

Engineering9

The Time We Cached Everything and Served the Wrong Data to the Wrong Customer

We built an aggressive caching layer for a Series B SaaS client to fix their latency problem. It worked perfectly — until one tenant started seeing another tenant's financial data. This is the story of the 72 hours that followed.

APR122026

Engineering8

What Actually Happened With Claude Code's Token Furnace Bug

Two caching bugs hit Claude Code simultaneously, silently inflating token costs by 10-20x. Users burned through monthly quotas in hours. Here is what broke, why it took days to acknowledge, and what every engineering team should learn from it.

APR112026

Industry13 min read

The State of AI in Insurance: 2026 Landscape

Insurance is one of the industries where AI automation is delivering measurable ROI at scale — not as a pilot but as core infrastructure. Here is what is actually deployed, what is still theoretical, and what the bottlenecks are.

Showing 10 of 152