AI Intelligence Archive

This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content ...

Every coding agent I tried could write files. None of them could use the computer. I'm an architect....

When we were given our project, CourierIQ, I knew I wanted to use it as an opportunity to learn...

Hello everyone! Today, I’d like to introduce a new version of EmbedCatalog. It’s a personal project...

Since software was first invented, many tech executives have relentlessly attempted to reduce the...

Stop Letting Your README Rot: Auto-Sync It on Every Push Every developer has lived this:...

AI coding agents like Claude Code and Codex can now work on longer tasks without supervision. That...

Hello! My name is Sergio, but everyone calls me Wolf. This is the first piece in a series I plan to...

The problem If you've built anything with LLMs, you've hit this wall: your data lives in...

A test named test_all_adapters_importable asserted nothing. It would pass forever, even if every...

Olá, DEV Community! 👋 Este é o meu primeiro post por aqui, e decidi começar abordando um dos tópicos...

AI helped me ship more this summer. Learning to stop has been harder. Between 15 June and 17 August...

I've spent the last while building MCQplex, an exam-prep platform for Nepal's NEB curriculum. Along...

The dangerous AI answer is not the one that fails. It is the one that looks right, reads with total...

anything2explainer gives Claude Code and Codex a staged Remotion workflow for narrated videos, with editable shots, four user checkpoints and bilingual output.

In 1988, a compiler was tricked into overwriting a billing file. Agents make the same mistake at machine speed.

I used to think becoming a better developer meant learning more...

AI-assisted development is rapidly moving beyond autocomplete and simple chat interfaces. We are...

Dantiva turns a photo into a short video. You pick a template, upload a picture, and a few minutes...

Hello, I'm Shrijith Venkatramana, and I'm building LiveReview — a blast-radius aware AI code review...

Built an MCP server that turns awwwards.com into an agent-readable design library. 7 tools over stdio...

Claude Code Session Compaction in 2026: How Context Summarization Works and What Your Agent...

A technical breakdown of using a local AI model + RAG to convert static HTML sites into installable...

I hired a marketing co-founder and she found me a job Not the plan. We're three people building a...

No. MCP doesn't replace APIs — it sits on top of them. An MCP server is, almost always, a thin...

Schema-valid is not content-correct · Part 1/3 It starts with a storyboard a...

I decided to build something around a subject that is very close to where I live: stećci, the...

Somewhere in the last few years, "good at your job" and "good at your craft" quietly stopped meaning...

Logan Markewich put out an open-source drop-in replacement for TypeSafe's jev API called jeff. It...

There's a particular kind of 2am I think every one of us knows. Not the heroic kind. Not the...

You are halfway through a coding project. Your AI coding agent has been working with you for hours,...

Disclosure: this post was written by the AI agent (Claude) that builds VetAgent with me, and...

This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange What I...

Every "AI code search" tool released this year does the same thing under the hood: chunk your repo,...

Jev returns a probability, not prose. That made it possible to model-check the consensus around it, then try to break it. Two of the bugs were mine.

What I Built Sanity‑backed Agent: Knowledge Navigator — an agent that answers precise,...

Why the same sentence can cost 3x more tokens in Hindi than in English — and what it actually takes...

A week ago I published a measurement: I had generated descriptions for 1,245 database objects to make...

Jev is getting wired into agents everywhere as the cheap typed-judgment layer (Choice/Score/Boolean...