Topic
467 articles found
I built a profiler to audit my own tool calls. After loading 157 skills in 12 days, I realized I had zero visibility into whether I was using them efficiently. So I built AgentLens. Most AI agent demos look magical because the demo is 30 seconds long. Run the same agent for a day and watch the logs.
Introduction Teams building content systems for regulated industries can now deploy multi-agent AI with confidence, knowing that every decision the system makes is auditable, constrained, and recoverable. That shift did not happen by accident. It took 12 months of iteration, three hard architectural
Series intro. I'm a non-CS solo dev who built and shipped a production stock screener almost entirely by "vibe coding" with an AI agent. The site works. Users use it. And it has cost me, in real ways, every shortcut I took. This series documents those costs honestly — what broke, why, what I shipped
I am implementing the Builder pattern in a Node.js (TypeScript) backend to instantiate a Permission object before passing it to my repository layer.I want to reuse this same Builder for both creating and updating a permission, but the presence of the id and the validation rules change completely dep
I vibe-coded my way through three months of Claude Code projects before I admitted something was off. The code worked, mostly, but I kept losing hours to the same problem: Claude and I would drift from the original intent mid-session, and by session two or three, neither of us remembered why we'd ma
In April 2026 Google shipped Gemma 4, a multimodal model with a native audio path. I wanted to add it to Parlotype, my .NET 10 dictation app, as a second speech engine alongside Whisper. Four runtime paths got cut before I landed on llama.cpp's llama-server as a child process. This post walks throug
REST API Design: Building APIs Developers Love (2026) A good API is like a good UI — intuitive, consistent, and a pleasure to use. 1. Consistency over cleverness → Same patterns everywhere → Predictable response shapes → No surprises 2. Resources, not actions → GET /users (not /getUsers) → POST /use
The first async AI application most Python developers write looks like this: import asyncio from anthropic import AsyncAnthropic client = AsyncAnthropic() async def summarize(text: str) -> str: response = await client.messages.create( model="claude-sonnet-4-6", max_tokens=512, messages=[{"role": "us
This is an excerpt. The full article includes a live YATA double-linked list simulator — type into two peer editors, toggle network partitions to simulate offline-first edits, and watch Y.js automatically resolve merge conflicts in real time. Read the full interactive version → Building real-time co
This is a submission for the Hermes Agent Challenge: Build With Hermes Agent SilentSpace Guardian is a local-first organizational entropy auditing platform that uses Hermes Agent Runtime to transform unstructured meeting requests into deterministic audit reports. The system combines: Hermes Agent Ru
This is a submission for the Hermes Agent Challenge It was a Tuesday. I gave Hermes Agent a research task before bed: "analyse the top open-source agent frameworks and write a comparison report." Reasonable task. Maybe 10 minutes of work. I'd check the output in the morning. I woke up to a $47 bill
Generic tech DD templates miss what actually kills deals in 2026: AI claims that aren't production-grade, architecture that won't survive 2× traffic, and eng teams that look senior on LinkedIn but can't ship. This checklist is what I use when doing independent engineering due diligence for VCs and a
When you call an external API, things go fine until they don't. A network blip, a server restart, a rate limit. So you add a retry, and most of the time it helps. The problem is that the obvious retry, the one we all write first, can quietly make things worse: it can resend a payment twice, or keep
This is an excerpt. The full article includes a live interactive schema sandbox where you can switch between 3 real constraint schemas and watch the Gemini inference engine stream constrained tokens in real time. Read the full interactive version → Language models are optimized to be helpful communi
The Operational Burden of JWT Lifecycle Management Every new technology that enters our lives initially excites us with its simplicity and promises. JSON Web Token (JWT) emerged as a great solution, especially for stateless authentication needs. However, over the years, I've begun to see more clearl
Imagine you’re building a personal research assistant. Its job is to ingest hundreds of academic PDFs, learn your unique writing style, and eventually draft comprehensive reports for you. When you first launch it, you connect it to a bleeding-edge cloud model like Claude 3.5 Sonnet or GPT-4o via Ope
The Problem We Were Actually Solving The real pain wasnt disk size; it was cognitive load on level designers. Every hunt lived in a separate fork of the same monorepo, diffing 14 kB YAMLs was misery, and once the file exceeded 100 kB we started getting partial-checkout timeouts in CI because Git wou
You log off for the day after two hours of research. You know the entry point is EvaluateSegments in targeting/segment/evaluator.go. You know the nil visitor_id case is unhandled. You know bidder/auction.go calls this function and can't have its interface changed. Next morning, Claude Code knows non
Here's something the container ecosystem doesn't say loudly enough: runc is not the only option, and for a growing number of production workloads, it's the wrong one. AWS Lambda doesn't run your function in a Docker container. It runs it in a Firecracker microVM. Fly.io's Machines? Firecracker fork.
Hey friends. Let's have an honest conversation about landing a tech job in the current market in 2026. The reality is that securing even a first interview now requires far more strategy, preparation, and persistence than it did just a few years ago. As I wrap up my current freelance work and watch A
