Blog

Insights on AI-native development and building SaaS products

Claude Code Cost in 2026: What It Really Costs and How to Cut Tokens
AI Development

Claude Code Cost in 2026: What It Really Costs and How to Cut Tokens

What Claude Code costs on each plan and on the API, where the tokens really go, and what a read-limiting hook and a Haiku subagent saved on a real repo.

Claude Code Memory (2026): How It Works and How to Make It Stick Between Sessions
AI Development

Claude Code Memory (2026): How It Works and How to Make It Stick Between Sessions

What Claude Code memory loads, what survives /compact, and where a rule actually gets followed, tested on three models. Plus a handoff skill and a prompt that audits Claude's memory.

OpenSpec Tutorial (2026): Spec-Driven Development in Claude Code, Step by Step
Tutorial

OpenSpec Tutorial (2026): Spec-Driven Development in Claude Code, Step by Step

Install OpenSpec, then run /opsx:propose, apply, and archive on one real API-keys change: every file it creates, the delta spec syntax, and the mistake validate won't catch.

Claude Code Not Following CLAUDE.md? 10 Causes and the Test for Each (2026)
AI Development

Claude Code Not Following CLAUDE.md? 10 Causes and the Test for Each (2026)

Ten verified reasons a CLAUDE.md rule gets ignored, from a stray CLAUDE.local.md to Cursor-only frontmatter, each with a 30-second canary test and the fix.

Vibe Coding Security Checklist: 12 Checks You Should Actually Run (2026)
Tutorial

Vibe Coding Security Checklist: 12 Checks You Should Actually Run (2026)

Twelve checks for AI-built apps, each with the command to run, what a failing result looks like, and what the fix costs. Built on 2026 breach data.

Claude Code Skills vs Subagents vs Hooks vs Workflows: Which to Use in 2026
AI Development

Claude Code Skills vs Subagents vs Hooks vs Workflows: Which to Use in 2026

Eight Claude Code primitives, one decision table: skills load into your window, subagents get their own, hooks run whether Claude agrees or not, workflows put the plan in a script.

What Is Agentic Coding? From Vibe Coding to Agentic Engineering (2026)
AI Development

What Is Agentic Coding? From Vibe Coding to Agentic Engineering (2026)

An AI agent that plans, edits, tests, and iterates on a whole task. How agentic coding differs from vibe coding, what Karpathy's agentic engineering adds, and a workflow that holds up.

AI Evals: How to Test AI Features Without a Research Team
AI Framework

AI Evals: How to Test AI Features Without a Research Team

Your unit tests mock the model, so they can't see the layer users actually touch. How to test AI features with golden datasets, a binary judge, and a CI gate that costs about $0.56 a run.

Why AI App Builders Hit a Wall — and What to Do Instead
AI Framework

Why AI App Builders Hit a Wall — and What to Do Instead

Lovable, Bolt, and Replit are validation machines that stall at production. Where the wall sits for each, what migrations really cost, and how to keep AI speed on a foundation you own.

AI Agent Examples: 6 Real-World Use Cases to Build in 2026
AI Development

AI Agent Examples: 6 Real-World Use Cases to Build in 2026

Six real-world AI agent examples that work as businesses today: support, sales, data, ops, and research, with the exact tools, data model, and approval flow to build each.

Loop Engineering in Claude Code: Let the Agent Run Itself
AI Development

Loop Engineering in Claude Code: Let the Agent Run Itself

Loop engineering means designing the system that runs your agent in a cycle. Drive a feature to done with /goal, run chores on a schedule with /loop and Routines.

pgvector vs Pinecone: Why We Chose pgvector for RAG in Next.js
Build in Public

pgvector vs Pinecone: Why We Chose pgvector for RAG in Next.js

We argued most AI agents don't need RAG, then we shipped it. pgvector vs Pinecone for a Next.js SaaS, when retrieval earns its place, and the copy-pasteable pgvector build.