Does Graph RAG Actually Help? I Measured It on Postgres and TypeScript
Graph RAG is usually described with one claim: vector search misses answers that sit behind a chain...
Tutorials
Introducing dim: A Better Runtime and Body for Agents
Today, we’re open-sourcing dim—an agent harness built around an event timeline. We want agents to...
A Maintainer's Advice on Contributing to Open Source in 2026
The ideal contributor As an open-source maintainer, you imagine the ideal contributor as...
I tried five agents to write one prompt. One agent did as well.
Nothing fancy: it is just one skill file that writes a prompt, or improves one, and attacks it before...
Lambda Web Functions Run an Ordinary HTTP Server With 128 Requests per Environment
TL;DR AWS Lambda Web Functions are a Lambda function type that runs a standard HTTP...
Our Multica agents now work in an agent market: they buy, remember, review sellers, and sell their own work
Multica is an agent factory: you give an agent a runtime, instructions and a schedule, and it works...
We Build a Compiler So You Don’t Have to Gamble on AI Getting It Right
We built a compiler, so you no longer have to rely on AI getting it right. It’s not that AI models...
AI crawlers don't run your JavaScript
GPTBot, ClaudeBot and PerplexityBot read the HTML your server sends and skip the scripts, so anything you render on the client simply isn't there for them.
How KV Cache Makes LLMs Fast, and Why It Eats GPU Memory
Every LLM you've used, ChatGPT, Claude, Gemini, Llama, does the same thing under the hood. It...
OpenRouter's Free Model APIs in 2026: Working With Request Limits Instead of Token Caps
Most developers hit the same wall once they start building with large language models. The prototype...
Ship with AI. Own What You Ship: Building Continuum to Solve Knowledge Debt
AI coding tools make it easier than ever to build software. A few prompts can turn an idea into a...
Your build attestation is a chain of custody, not a safety certificate
Picture a release with a perfect paper trail. You have the reviewed commit, the resolved...
Galaxa - Building a BBC Micro game with AI
As a kid I made a BBC Micro game that got published in Computer and Video Games magazine (C&VG)...
Deploying AI Models Explained: Versions, Canaries and Drift
A team deploys a new version of the AI model behind its support agent, the one that handles...
WebMCP Attack Lab: Can an E-Shop Hijack Your AI Agent?
WebMCP is a proposed web standard that, at least to me, looks very promising. I already played around...
Human in the loop AI: testing if a prep note moves the forecast
This is a small test harness for human in the loop AI, where the human reads what an agent wrote and...
Trying to break into the clinical trials space
Imagine someone has just been given a serious diagnosis. One of their options might be a clinical...
Are We Becoming Developers Who Can't Actually Code Without AI?
Let's ask ourselves an uncomfortable question. If AI disappeared tomorrow, would you still be the...
The first proof no human could read
I built a small thing this week: a page that colors a map of the United States so that no...
What Does Multi-Turn Reinforcement Learning Really Improve in LLM Agen: Deep Dive & Engineering Breakdown
What Does Multi-Turn Reinforcement Learning Really Improve in LLM Agents? If you have...
7 Ways Coding Agents Turn a Red Test Green Without Fixing the Bug, and the grep for Each
Claude 3.7 Sonnet's system card reports it special-cased tests. Seven ways an agent fakes a green suite, and a git diff grep that flags each one.
Debugging Is the Skill AI Made Most Expensive to Skip
Writing code got cheap this decade. Debugging it did not. In the 2025 Stack Overflow survey, 45% of...
My Agent Said 'All Tests Pass.' CI Disagreed Three Minutes Later. Both Were Honest.
The agent says all tests passed. Three minutes later, CI says otherwise. And the part that takes a...
97 of 99 Sounds Great. It Would Have Been a Bad Release Number.
From the agentpolicy v0.1.0 release: a local-first, Cedar-based policy decision point for AI agents...