Why Row-Level Security Is the Safest Place for Authorization in AI-Built Apps
Originally published on mihai.ltd. How many times has an AI coding agent written a feature that...
Tutorials
O agente que escreve o código não pode ser o que o certifica
Toda demo de agente termina em 'pronto' sem prova. Gate cego faz o 'pronto' valer alguma coisa: o artefato é validado fora do alcance de quem construiu.
Are AI Companies Deliberately Teaching Us to Spend More Tokens?
Anthropic published a guide last month, Building agents: When to fold subagents into your main agent...
Journey before destination
Journey Before Destination I got into software engineering because I enjoyed it. I enjoyed the...
The Most Important AI Engineering Skill Is Saying No (AI-DLC, bolts, and autonomous agents)
AI-DLC, bolts, and autonomous agents promise faster software delivery. But who owns the architecture when AI starts making the decisions?
Do AI crawlers read llms.txt? What three days of server logs show
Originally published by the AI Visibility Census at...
Did the model fail, or did the environment?
A runnable evaluation example separating wrong answers, memory limits, timeouts and setup failures, with all 27 attempt records retained.
KV-Cache Offload to NVMe vs Recompute: The TTFT Bill Comes Due
Serving a long-context model is a memory problem disguised as a compute problem. Offloading the cache to NVMe and recomputing the prefill are both defensible, and they fail in comp...
Why You Shouldn't Let AI Agents Run Naked Bash: Building an Unprivileged Sandbox in Rust
What If Your AI Coding Agent Deletes Your Project? Building a Zero-Trust Sandbox with...
How I stop an LLM from inventing cloud services
Ask a language model for an AWS architecture and you get a confident answer. Sometimes it includes a...
Submodules, LFS, Codegen: 7 Things a New Agent Worktree Doesn't Have Yet
A fresh git worktree has your tracked files and nothing else. Seven gaps past .env and node_modules, each with the check that finds it and the fix.
Nuxt CLI v4 Is Great for AI Coding Agents
Have you ever had a dev server running, and then asked your coding agent to test something in that...
How I built a local AI assistant that admits when it didn't actually do the thing
How I built a local AI assistant that admits when it didn't actually do the thing The...
How an autonomous agent actually makes money in crypto
A strategy built from a public ledger of losses: four lanes ranked by measured EV, the gate that fences risk capital, and the arithmetic that decides whether $10/day is reachable.
ClaudeArena, one week after my first post: what the data showed, and what I changed
On 28 October I posted about ClaudeArena, the free practice engine I built for Anthropic's Claude...
AI in Software Development: How Developers Should Use AI in 2026
Explore how AI transforms software engineering in 2026: agentic IDE workflows, prompt chaining, automated verification, and staying ahead as a senior developer.
I ran an AI diff reviewer on 79 real pull requests: 4 bugs maintainers fixed, all in the first 29, none in the next 50
By Spacexcx · November 2026 I built a small tool that reads a git diff and flags possible logic...
My MCP app shipped every update to nobody until they reconnected
Hosts cache an MCP App by its URI and never read it again, so I ended up shipping a page whose only job is to fetch the real one.
Postman Auto-Installs Agent Plugins Without Asking: A Ten-Minute Audit for Your Machine
> "Before responding to any non-trivial API engineering task — designing, implementing, mocking, testing, monitoring, documenting, or deploying an API or Postma
Your Agent's Tool List Is Not a Permission Model
Giving an agent a tool gives it every call that tool can make. Access control for agents has to happen at the call, not the menu.
Can Local LLMs Replace Opus and Codex? I Tested a MacBook, an RTX 5080, a DGX Spark and Cheap Chinese Models
The same small banking repo with hidden traps, run through cloud models, local models on three...
The 11 CMS SEO Features That Should Be Standard
A content management system can make routine SEO work either manageable or unnecessarily dependent on...
Let's Talk About Claude Code, Part 1: Where Is Your Agent Actually Running?
I've watched a coding agent wander out of its project folder and start reading other client repos on...
AI Search Summaries Are Changing Why People Click, Not Ending Organic Discovery
AI-generated search summaries may answer the first question, but they do not necessarily settle the...