AI Coding Agents Now Ship Software. Plugin4Shell Shows Nobody Checks the Package
TL;DR On September 17, Air Security disclosed Plugin4Shell, a zero-click, high-severity...
Tutorials
Prompt Pad: Lock Your AI's Output Schema in Google AI Studio
If you've ever tried to parse an LLM response in code, you know the pain: the format changes slightly...
ChatGPT now searches for 'official' and 'price' more than 'best'. Your comparison pages need to change.
The SEO playbook says: write "best X for Y" listicles because that is what people search for. The...
Your Agent Has a Side Door: Testing MCP Policy Beyond the Tool List
At MCP Dev Summit Toronto, Accenture's Michael Forrester told a story about an employee who wanted...
Your agent's slowest tool call may be waiting for you
An agent takes twelve minutes to finish a task. The tool report shows twenty minutes of activity. One...
Rack Before You Remember
What racking wine teaches about agent memory The mead's lees on October 21, with the racking cane...
Corporate PowerPoint decks with AI, for free: slides as code, QA as the gate
An open-source factory that lets your AI agent write native, editable .pptx files and then checks them before anyone sees them: text overflow, contrast, story and charts.
Your agent loaded a skill. Did it actually follow it?
Installing a skill answers one question: is it available? It does not tell you whether the agent...
Stop trusting your AGENTS.md: the drift-check that makes it a contract
Back in September I published Stop bloating your AGENTS.md: reference your conventions instead of...
OpenRouter Alternatives: 5 AI API Gateways Worth Considering in 2026
When an application sends requests to more than one AI model, keeping those integrations organized...
I Let AI Build a Feature Without Giving It the Full Context
If you give an AI a vague prompt, it will give you a confident answer. And that confidence will cost...
I Asked Coding Agents the Same Open-Source License Questions 36 Times. Casual Prompts Failed 3/3.
While building a checklist of open-source software for small teams, I kept hearing the same...
The Workflow That Sent It Twice: Reconciling Side Effects After a Retry in n8n
This is part of my build-in-public series on running LLM workflows in n8n in production. Everything...
How I keep faces the same when editing photos with Nano Banana and GPT Image
The most common complaint about AI photo editing is not quality. It's "that's not me anymore". You...
[AI in Action] Rewriting a Daily LINE Bot from Python to Go 1.26 on Cloud Run: 1/4 Resource Usage, Google ADK v1.9.0, and Zero-D
Background I have a primary LINE Bot that I use heavily every day:...
[AI in Practice] Rewriting a LINE Research Bot from Python Managed Agents to Go ADK v1.9.0: From Sandbox Files to Session State,
Recap In the previous post "Comprehensive Analysis of Managed Agents API", I created an...
Your AI-built Next.js 16 landing page looks fine. Its link preview might not: 6 metadata traps and the prompts that fix them
An AI-built Next.js 16 landing page can look perfect in your browser while its link previews,...
My agent's dry-run wrote seven texts to production. The fix was already on the remote.
On September 15 at 10:27 UTC, an agent working for me ran a dry-run seven times, once per language of...
Cut your Claude Code bill without losing quality: what 100 measured runs say about effort levels
TL;DR. Since mid-September 2026, Claude Code's weekly limits have been cut and reports of quotas...
Do AI-Written Tests Actually Catch Bugs? I Measured It
LLMs wrote pytest suites for three Python projects; every suite was scored against one fixed mutant set. Green suites sometimes killed zero mutants.
A kanban board for AI coding agents: 12 stages, 6 repos
Orch2 turns a ticket board into the control panel for coding agents: a plain script runs 12 stages, agents only write code, and every ticket gets a sa
Our LLM filter looked broken under load. It was a billing short-circuit returning {} in 0.0 seconds
We build Leadolovets, a service that reads open Telegram chats and pulls out buying intent: "who does...
An AST fingerprint and an embedding model both look for duplicate code. Here's where each one is wrong
We run two duplicate finders over our TypeScript repos. One is static: it parses every function,...
Your agent tool guard probably fails open. One minute to tell.
A gate in front of an agent tool call often passes the dangerous call when the script is missing, when it crashes, or when it exits 1. Here is a four-probe check, what an exit code...