We're Putting AI Everywhere Before It's Sustainable
Orignally posted on amarpandey.me We are making an expensive, resource-intensive technology...
Tutorials
Skill Inspector: ESLint for your AI agent skills (SKILL.md)
Agent skills are turning into config files. A SKILL.md has some frontmatter, a few instructions and a...
Does Static Typing Reduce AI's Bugs? I Had Claude Code Build the Same Git Clone Three Times Each in TypeScript and JavaScript
A follow-up to "Which Programming Language Is Best for Claude Code?": at a few thousand lines, the gap between TypeScript and JavaScript mostly disappeared.
My coding agent set up auth five times, five different ways. So I gave it my working version
Every new project starts the same way. I ask the agent to set up auth, and it writes it from scratch...
How I built an opt-in Modal (DeepSeek) provider for my desktop AI companion — then benchmarked it and kept the old one
How I built an opt-in Modal (DeepSeek) provider for my desktop AI companion — then...
I Attacked a Real LLM Agent With Hidden Text. Here's What It Did (Free Kaggle Notebooks)
AI agents read things: documents, emails, web pages, tool results. Then they act: send emails, call...
Stop telling agents not to do dangerous things. Remove the capability instead.
In April 2026, a Cursor agent running Claude Opus 4.6 deleted a startup's production database. The...
I gave my AI agent a memory. It started seeing patterns that weren't there.
Memory is the feature everyone wants to add to their agent: remember what happened, stop repeating...
Reading Agent Transcripts for Real Observability, Without Instrumentation
What an agent's transcript can and cannot tell you, and how to spot hedged claims, missing output contracts, and silent errors just by reading it.
I deleted plan.md. My AI agent now plans, logs and proves its work in one file.
One progress file, a timeline pane beside the chat, and the rule that a box is ticked only with proof.
WeKnora: turn scattered documents into one queryable knowledge system
WeKnora Most teams do not have a knowledge problem. They have a scattered documents...
A Trusted Public Certificate Authenticates as Any LXD Client
TL;DR LXD is a manager for system containers and virtual machines that runs on a Linux...
An LLM Wiki That Keeps Context When the Session Ends
How several AI agent sessions build up and reread context in one Obsidian wiki.
TypeScript Does Not Protect Your API: Request Bodies Are Lies Until You Validate Them
You write a clean endpoint. The body is typed. The editor is happy. No red squiggles...
A harness grown from losses
I almost never see the auto-compact warning in Claude Code. That is not a setting. I dislike what...
Allow, Ask, or Block: The Week Agent Security Moved to the Action
Allow, Ask, or Block: The Week Agent Security Moved to the Action The security...
When did you last code a project fully by hand ?
Recently I attended my first AI meetup in my city and I loved it really loved it. I walked out with...
How I shipped a remote MCP server on Cloudflare Workers (and got it into the Registry)
I run Bilingual Mix, a small tool that turns parallel text into sentence-by-sentence alternating...
ChatGPT referrals convert at 15.9%. Google organic converts at 1.76%. The AI channel is small but 9x more valuable
Seer Interactive measured ChatGPT referral traffic converting at 15.9% versus 1.76% for Google...
My bug reproduction agent trusts the container, not the model
A quick update since this first went up on AWS Builder Center on Nov 6: Phase 3 passed its gate that...
How I Handle Ambiguous API Timeouts in an AI Video App
A video-generation request times out. There is no task ID in the response. Should the application...
Don't Write More Prompts. Install These 10 Trending 'Skills' Instead
I found 10 trending skills on GitHub that can boost your agent power a lot, and I had to test them...
I Built an Open-Source Safe Multisig Sentinel in n8n (Without Giving an AI Private Keys)
How I built a 24/7 treasury operations watcher that ingests Safe webhooks, diffs baseline configurations, and uses an AI explanation analyst without storing a single private key.
Stop Blaming the LLM: Why Most RAG Failures Are Retrieval Architecture Problems
Every time an enterprise Retrieval-Augmented Generation (RAG) system produces a hallucination, drops...