How to build a secure, cross-protocol Agentic AI cluster in 15 minutes (without touching Istio).
The Challenge of the ReAct Loop (East-West Traffic) A ReAct loop is essentially an AI...
Tutorials
I Built an OpenAI-Compatible Gateway to Control LLM Costs
As an indie developer building AI products, I kept hitting the same wall: how do I control LLM...
Cursor has an unpatched 0-day. It's been 7 months.
A developer opens a repository in Cursor on Windows. If that repo contains a file named git.exe in...
AI Replaced Me -- Just Not the Way You Think
AI replaced me. Not the way you think. I'm still a software engineer. But the work I used to do in...
The AI Jackpot: Why Prompting Feels Like Gambling
This is more of a thought experiment than a firm stance. I’m not really here to be pro-AI or...
🚀 Building Two AI-Powered Solutions at HACKHAZARDS '26: VeritasFlow & PermitFlow
🚀 Building Two AI-Powered Solutions at HACKHAZARDS '26: VeritasFlow & PermitFlow How...
The Chatbot Was Easy. The Engineering Wasn't.
Part 1 of a series on building a production banking AI chatbot. When our team kicked off the...
I source-reviewed 200+ self-hosted AI tools for tenant isolation. 78 leaked across tenants.
The same isolation flaw, the un-retrofitted read sibling, in 78 of 200+ multi-tenant AI and SaaS...
# Tracking the Ghosts in the Machine: Instrumenting Asynchronous AI Agent Workflows with OpenTelemetry and SigNoz
When an LLM-based agent takes 12 seconds to respond, where exactly does the time go? Was it a slow...
Why LLM Decisions Should Be Deterministic
TL;DR: I originally treated deterministic boundaries around LLMs as a consistency mechanism. I now...
Are Bigger AI Models Actually Making Developers Faster?
It's no secret that AI models have come a long way since the early days. They've become one of the...
The Trillion-Parameter RL Paper Is Really About Letting the Model Find the Workflow
A practical read on Ring-Zero, zero RL at 1T parameters, and why the useful lesson is feedback loops over prompt scaffolding.
Why Not Every AI Application Needs Vector Embeddings
How building an AI chapter generator taught me to stop reaching for a vector database first. When I...
Your AI built something private. A public link is the wrong way to share it.
Building with AI got fast. You describe a thing, and a page, a dashboard, a small internal report, or...
17 PRs a Day, One QA: How We Automated E2E Failure Triage
Picture this: 18 AI-augmented developers merging an average of 17 pull requests every working day —...
A plugin can pass validation and still fail after install
Five package-level failures that can survive a plugin manifest check, and a read-only way to catch them across Codex and Claude Code.
Resources for reading, tools for acting: the MCP design choice most servers get wrong
Every tool you expose over MCP ships its full definition (name, description, JSON schema) into the...
Agentic Is Powerful. The Bill Is in the Tokens.
Agentic workflows are useful. The problem is how fast tokens pile up. A single do this can turn into...
Teaching a Qwen agent to forget
Every AI photo tool today is an amnesiac critic. Lightroom edits, culling apps, and...
My MCP Server Only Talks to APIs I Trust. That Doesn't Mean the Data Coming Back Is Trustworthy.
I built a small MCP server a while back — developer-presence, seven tools wrapping the GitHub REST...
My Commit Message Generator Kept Signing Its Own Work. Telling It Not To Wasn't the Fix.
I have a script called git_commit.py in one of my repos. It shells out to claude -p with the staged...
Building a Research-Grade AI Project as a Solo Developer: My Stack, Tools, and Workflow
I used to think “research-grade” meant a big lab, a cluster of GPUs, and a team of people each owning...
Building a production MCP server: How we made GoodBarber agent-ready (without the glue code)
We wanted an AI agent to manage a real production app (its content, its catalog, its push...
Building AI That People Actually Use: Lessons Beyond the Hype
Artificial Intelligence has become one of the most talked-about technologies of our time. Every day...