Your Claude Code subagents pay for...
...your CLAUDE.md on every turn again, and again. and...
Tutorials
What an AI shopping agent sees in your store (and the 45 checks we built to find out)
Your next customer doesn't scroll Retailers have a habit called a store walk. The manager walks the...
Why One Emoji Breaks Your Coding Agent's TUI Borders: wcwidth vs Grapheme Clusters
A 2025 emoji shifted Claude Code's TUI one cell until a width-table update. How wcwidth, VS16, ZWJ and mode 2027 decide where your agent's borders land.
How to Build a Marketing Analytics Dashboard That Answers Questions AI Cannot Guess
Stop building dashboards that look impressive but leave your team asking, “So, what should we do...
I built an MCP server for restaurant bookings, and it never books anything
I’ve worked in Sydney restaurants and bars for over a decade, with every kind of booking app open at...
Small Models Do the Chores, Big Models Give the Answer: Cost by Task Split, Not by Model Size
Most teams pick one model and send it everything. That is the expensive mistake. The question is not...
Tracking cost per finished job, not per token: the 3 fields I log
Most teams instrument their agents down to the token. Almost nobody instruments the one bit that...
Your MCP server can change what it does between versions — and you won't know
MCP exploded: by mid-2026 there are 10,000+ public servers. But trust in the ecosystem is...
I paper-tested an AI memecoin trading bot for 2 days. Here's what the safety checks caught, and what they didn't
On November 1 a post went around X claiming an AI agent had turned $280 into $3,412 overnight trading...
I built an open-source tool that lets your coding agent film screen recordings
I like Screen Studio-style videos: a smooth cursor, zooms that follow the action, a nice gradient...
The AI endpoint that charges you money when somebody abuses it
Abuse of a normal endpoint costs you capacity. Abuse of an endpoint that calls a model costs you money per request while everything looks healthy. Four controls, and the quota bug ...
Claude's API Now Holds Your Agent's Conversation for 5 Minutes. Keep Your Own Copy
Claude's message threads beta sends only new turns and, by Anthropic's count, cuts wait on huge sessions ~35%. Price is unchanged and the thread expires fast.
I looked inside a small AI model to find where luck changes its answer
In my last article, AI judges scored the same decision lower when it happened to end in harm. I...
ClaudeBot, GPTBot, ChatGPT-User: which AI crawler does what
Open your server log and you find names like ClaudeBot, GPTBot, ChatGPT-User, OAI-SearchBot and...
I Gave an AI Agent Full Access to My Repo for One Week. Here's the Incident Report.
On Monday, I gave an AI coding agent full read/write access to my side project with one instruction:...
How I built a vision-token trimmer that prices images for one provider — and a reader caught it
How I built a vision-token trimmer that prices images for one provider — and a reader caught...
I let the LLM read the loan question, never do the maths
People don't think about loans in form fields. They think in sentences: "What's my EMI on a 20 lakh...
Наш ИИ-агент не знает цену тура. И это главная фича
Лид. Если спросить LLM про тур на Камчатку, она уверенно назовёт цену, даты и свободные места. Беда в...
A remote MCP server in ~100 lines, no SDK (on Cloudflare Pages)
I run four small single-purpose sites: a Discord timestamp generator, a zalgo text generator, an...
How Much Does It Cost to Build and Run an AI Agent for Your Business?
A $200 software subscription and a $7,500 agent deployment put different things in your budget....
Day 14/90: Your AI Agent Has a Tool Permission Problem — Not Just a Tool Calling Problem
I explored why defining input and output schemas is not enough to make AI tool calling reliable. But...
Why developers mute AI code reviewers (and what I changed to stop it)
Every team I talked to had the same story about AI code review bots: they installed one, it posted 25...
How to test a web app built with Claude Code or Cursor before you ship
A step-by-step way to check that agent-written code still lets users sign up, log in and pay: critical flows, hooks, preview deploys, browser and API checks.
What our analytics SDK receives from your server, field by field
"We only collect what we need" is a sentence every analytics vendor writes, and it's unfalsifiable....