Designing MCP tools for a stateful app: what I learned building an AI-editable video timeline
Most MCP servers wrap something stateless: search an API, read a file, query a DB. I built one for...
Tutorials
What validators miss when a coding agent writes your HTML
Ask a coding agent for a "Save" button and you sometimes get this:
We put a 1.6 KB AI in a QR code, a favicon, and a WAV
The same 160-word SMS spam model in five containers: a QR URL, a 32x32 favicon, a WAV, a spreadsheet, and a single HTML file.
Developers Swear AI Makes Them Faster. A Stopwatch Says They're 19% Slower
There are two completely different AIs — the one you're forced to use and the one an expert chose — and we keep confusing them. Five measured findings, the methodology behind each,...
Amazon Dev News • Vega Guides & Netflix AI Discover • Nov 9, 2026
With the Vega 2.0 launch last week, we have a bunch of new docs and videos for you, including guides to Hello World and OS compatibility, and videos on What's…
The API Said "Model Not Found." The Model Existed. The Bug Was a Query String.
Wiring a DeepSeek gateway into a Claude Agent SDK app broke with a misleading "model does not exist" error. The real causes: a ?beta=true query param, and an unmerged assistant mes...
Our Looping Factory Cut DEV Page Load Time by 75% and Counting
A month ago, an average web request on DEV took about 70 milliseconds inside Rails, with P99 response...
Entourage
You head to the dog park with your dog Charlie on leash. You greet other dog owners there, and let...
One polite email taught my Hindsight agent to pay scammers
One polite email taught my Hindsight agent to pay scammers The email that broke my agent had no...
Spec to PR with Claude Code: what the agents decide, and what I still decide.
A pipeline of single-purpose subagents that hand off through files on disk, with gates that...
Only the Design of a Local LLM Eval Harness Survives — Rebuilding It for Qwen3.8 27B
Three weeks ago I wrote an RFC 6902 porting harness to decide whether to keep Ornith. I reused it to evaluate Qwen3.8 27B — except the script itself had vanished with /tmp, and reb...
Introducing NovaDesk AI: Building a Stateful Hotel Concierge with LangGraph
When you start learning Agentic AI, you quickly hit a wall. Most tutorials show you how to build a...
Why Developer Experience (DX) Isn't Enough in 2026: You Need Agent Experience (AX)
What happens when the hardest-working user on your 16GB Mac and multi-cloud Ubuntu Dev-Box is a fleet of 20+ AI coding agents? Real benchmarks and fixes for 8s Chrome 136+ CDP hang...
I built a private video-to-GIF converter that runs entirely in the browser
Most online GIF makers upload your video to a server, add a watermark, and bury the download button...
I built an MCP server so AI assistants stop guessing Dutch health insurance prices
Ask an AI assistant what the Dutch mandatory health insurance deductible is for 2027 and you'll often...
9 AI Workflow Automaton Tools Compared for 2027
AI workflow automation tools connect your apps and add a model to the steps in between. This way, a...
How I Tested Hindsight Memory Without Fooling Myself
How I Tested Hindsight Memory Without Fooling Myself An agent with memory looks smarter in almost any...
“Hindsight Stopped My On-Call Agent From Repeating a Failed Fix”
"A practical incident-triage design that remembers failed fixes, not just successful ones, so an...
Per-agent tokens for MCP servers: what operators told me, and the design that came out of it
A few weeks ago I set out to give every AI agent its own cryptographic identity. Then I asked the...
Self-heal broken locators with a 2B model on your own GPU
Qwen3.5-2B with a LoRA heals broken UI-test locators in Optics Framework 1.11.3. A direct weight edit added 1.6 points. The LoRA added up to 7.
How a paid MCP server can charge AI agents safely (what we learned building one)
I'm the maker of AwesomeVideo, a hosted captioning API and MCP server that agents pay for with...
We let an AI red-team our hardware encryption. Here's what it found.
I build Crypt-in alone, in Bologna. It's file encryption anchored to a €5 ESP32-S3: the root secret...
Day-0 Model Support Is a Fork: What 26 NVIDIA Dynamo Snapshot Builds Say About Pinning Your LLM Serving Stack
I read 36 Dynamo release notes. Stable pins trail vLLM by a median 30 days, and 16 of 26 model snapshots sit on patched or custom engine bases.
Everyone Is Building AI to Replace Developers. Nobody Is Building the Plan for What Comes After.
Quick game. Open the launch post for any AI coding tool and count the verbs. Generates. Refactors....