Context Window

Intelligence about AI, digested.

May 14, 2026

Opus 4.7 Reels Us Back In

Plus: The ‘Mini Shai-Hulud’ breach, a small step to eliminating AI-isms, and how we define ‘agent’

May 13, 2026

Mining Your Life for Context

Plus, how Every’s head of growth stays focused and some aggressively casual language

May 12, 2026

The Fallacy of the 16-hour Agent

Plus: Perplexity’s rules for agent skills, the office politics of dictation, and creating a weekend AI piano coach

May 10, 2026

AI Work Is Splitting in Two

Plus: Anthropic’s agent push, ChatGPT as project manager, and optimism in biotech

May 6, 2026

OpenAI Flips the Script

Plus: Permission to skip model-migration anxiety, why being an early adopter is overrated, and the importance of curiosity in an AI-saturated world

May 5, 2026

The Dawn of Codex-native Apps

Plus: Delegation versus collaboration, Dan’s inbox-zero Codex workflow, and the agentic version of Musk’s five rules of automation

May 3, 2026

Codex Goes to Work

Plus: Agent-native product management, AI cost discipline, and medicine at the speed of software

Apr 30, 2026

Who Isn’t Using GPT 5.5

Plus, the CTO-to-IC pipeline and GPT-5.5 one week in

Apr 29, 2026

Compute Is the New Cash

Plus: The end of the AI subsidy, do you actually want to talk to your agent, and how to turn customer feedback into a product queue

Apr 28, 2026

One App to Rule All Knowledge Work

Plus: Agent-designed automations, why final review belongs in the destination app, and how to use our compound knowledge plugin

Apr 24, 2026

Codex Moves Beyond Coding

Plus: Our GPT-5.5 benchmark, Monologue Notes, and becoming terminal-pilled

Apr 24, 2026

Model Wars

Plus, the AI tell that’s exploded in company documents, a skill for creating product videos, and comics

Apr 22, 2026

You’re the Bread in the AI Sandwich

Plus: Trust batteries, and how many agents we’ll have in the future

Apr 21, 2026

Mini-Vibe Check: Claude Design Isn’t for Designers—Yet

Plus: Vercel and Lovable’s security woes, and how to make your agent your watchdog

Apr 17, 2026

The Model Got Stranger

Plus: Using NotebookLM to run the Pyramid Principle in reverse

Apr 16, 2026

You’re the Manager Now

Plus: Why small models can't match Mythos, an AI workflow confidence check, Claude Code token tracking, our agent-muting plugin, the AI philosopher draft, and a mini-Vibe Check on Dia

Apr 15, 2026

Mini-Vibe Check: Claude Managed Agents Handle the Infrastructure Work

The case against LLMs, and new words for our AI age

Apr 11, 2026

The Missing Layer in AI Adoption

Plus: How Every runs on four agents—and what happens when everyone gets one

Apr 8, 2026

Every Is Half Agent Now

We’re writing the etiquette for agent-human collaboration in real time

Apr 7, 2026

Get Your Hands Dirty

Plus: Why Anthropic is shutting out third-party agents, and OpenAI isn’t

Apr 5, 2026

House Rules for the Agents

Plus: We Vibe Checked a reimagined Cursor

Apr 1, 2026

If SaaS Is Dead, Linear Didn’t Get the Memo

The product management tool has successfully reinvented itself as an agent-native business

Mar 29, 2026

Everyone Gets a Sidekick

Plus: The best from our Q2 Demo Day

Mar 26, 2026

Your Claw, Yourself

Plus: OpenAI is back in the coding race

We use analytics and advertising tools by default. You can update this anytime.