Reading List

I Built a Monster CLAUDE.md, And My Coding Agent Got Scary Good

Meet the new Copilot Studio: rebuilt for more complex, multi-step work | Microsoft Community Hub

A new streamlined authoring experience and modern AI core make it easier to build agents and workflows that deliver more consistent and reliable outcomes.

To Preview or Not to Preview? Copilot Studio Reality Check

Microsoft has been steadily evolving Copilot Studio throughout 2026. With the launch of a new visual workflow canvas and an AI-driven agentic orchestrator, Microsoft has fundamentally reimagined the platform. This evolution moves Copilot Studio beyond basic conversational chat, transforming it into a robust hub for 'Work IQ' and autonomous, multi-step business execution. This article offers a […]

AI Economics for Dummies

“Xavier owns an apartment that he rents out at a loss of $1 billion/month. Seeing this success, he decides to make financial commitments to construct $850 bi...

Netflix engineer Tejas Chopra creates Headroom, an open-source tool that compresses AI prompts to reduce token costs, and estimates it has saved users $700,000

Chopra, a Netflix senior engineer, built Headroom to prune redundant tokens from prompts before they reach language models. He estimates that as much as 90% of tokens are redundant. The tool, not an official Netflix project but already used by several Netflix teams and external projects, has been available since January and currently stands at v0.22, with 2,000 GitHub stars and over 120 forks.

How Microsoft is migrating repositories to GitHub - Azure DevOps Blog

For the past decade, Azure DevOps has powered software development at Microsoft, supporting some of our largest repositories and most complex engineering

Opus 4.8 Made Claude Smarter. Token Discipline Got Urgent.

I’m Matt Burns, Chief Content Officer at Insight Media Group. Each week, I round up the most important AI developments,

I set up Claude Code the way Anthropic showed at Code w/ Claude, and it'll change your workflow

Who better to copy than the team shipping it every day?

Mystery company accidentally blew $500 million on Claude AI in a single month — failed to put usage limit on licenses for employees | Tom's Hardware

A new report claims AI is getting too expensive for big companies

What we learned using AI agents to refactor a monolith | 1Password

1Password used AI agents to help refactor a massive codebase. The project taught us several lessons about where agents are useful and where they fall short at each stage of the process.

The 4 Lines Every CLAUDE.md Needs

What Karpathy diagnosed, what 60,000 developers bookmarked, and why behavioral constraints beat feature checklists

Introducing fulgur: a blazing fast HTML-to-PDF engine in Rust — no browser required

How I built fulgur, a Rust HTML-to-PDF engine on top of Blitz + Krilla - 200-page docs in 190ms with 57MB memory, no Chromium required.

The Pulse: token spend breaks budgets – what next?

In the past 2-3 months, spending on AI agents has exploded at many tech companies, Details from 15 of them, including the different ways they are coping with this realization.

Amplifying — Coding Agent Intelligence

Research on what dev tools AI coding agents actually recommend. Amplifying runs Claude Code, Codex, and Cursor against real repos and tracks which tools win by default.

Opus 4.7's New Tokenizer: What It Actually Costs | OpenRouter

The unified interface for LLMs. Find the best models & prices for your prompts

Embed Copilot Studio Agents in Canvas Apps with a PCF Control

The built-in Copilot control for Canvas Apps is deprecated. Use this PCF control to embed your Copilot Studio agent with custom styling and two-way communication.

Google makes DESIGN.md open source on its way to become a industry standard

Last week, I wrote a post titled ‘Design.md as a standard’ and it’s not like I have inside contacts at Google… or do I? Well, I do, but…

An update on recent Claude Code quality reports

Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.

The Non-Technical Person's Guide to Building AI Automations

A step-by-step guide to building AI automations with nothing but plain English (two templates included).

How The Heck Does Shazam Work? (An Interactive Exploration)

Explore how Shazam and song identification work through interactive visualizations - spectrograms, constellation maps, hash fingerprints, and time-offset matching.

Vercel confirms breach as hackers claim to be selling stolen data

Cloud development platform Vercel has disclosed a security incident after threat actors claimed to have breached its systems and are attempting to sell stolen data.

AI Was Supposed to Make Engineers Less Burned Out. The Data Says Otherwise.

Every major AI company publishes research showing their tools save developers hours every week. Our...

12 Agentic Harness Patterns from Claude Code

The leaked source revealed how a production coding agent is actually assembled. Here are the design patterns behind it.

How does Claude Code *actually* work?

We keep talking about Codex, Claude Code, Cursor, etc. But how do they actually work?Thank you Macroscope for sponsoring! Check them out at: https://soydev.l...

Claude Code Has an Internal Skill Nobody Knew About: /skillify

TL;DR: npx skills@latest add Vesely/skills/skillify and then just use it /skillify

Porting Mac OS X to the Nintendo Wii

Mac OS X 10.0 (Cheetah) running natively on the Nintendo Wii

The AI Great Leap Forward

In 1958, Mao ordered every village to produce steel. The steel was useless. The crops rotted. Today's top-down AI mandates are producing the same pattern: ba...

Claude Mythos and the end of software

I....yeah. It's all over now.Thank you Blacksmith for sponsoring! Check them out at: https://soydev.link/blacksmithSOURCEShttps://www-cdn.anthropic.com/53566...

Project Glasswing: Securing critical software for the AI era \ Anthropic

A new initiative to secure the world’s most critical software and give defenders a durable advantage in the coming AI-driven era of cybersecurity.

Inside Anthropic’s biggest design choices

On the latest episode of the ‘By Design’ podcast, Joel Lewenstein, Anthropic’s head of design, shares how he thinks about the role of design (and designers) in a rapidly changing landscape.