More people need to laugh with me at this

Fable is my favorite model ever. Stuff that never worked suddenly works. The factory is running! Feedback from Slack -> auto-processed -> PRs written –> merged while I sleep. Showing how it runs using @claudeai and @cursor_ai 👇

put me in coach @RickRubin

This is a major step toward true atom by atom manufacturing: researchers placed individual carbon atoms with atomic precision to build custom structures on a silicon surface. They successfully built tiny custom structures (including an “X” shape made of 18 atoms) and even short chains of carbon atoms, all with incredible accuracy at the single atom level. This is significant because it overcomes a long standing challenge in nanotechnology (often called the “sticky fingers” problem), where atoms tend to stick unpredictably. By carefully donating carbon pieces in a controlled way, they achieved programmable, precise assembly at the atomic scale. While still in the early experimental stage (done at very low temperatures in a vacuum), this work brings us closer to the long held vision of molecular manufacturing — the ability to construct almost anything by assembling atoms like LEGO bricks. 📸 Megan Cowie, et al. / CBN Nano Technologies Source: futuretimeline.net/blog/2026…

This is true. I came back to Compound Engineering after a hiatus, and right from the jump it was obvious that it was better that whatever I was doing with Claude/Codex before - but only obvious because there were comparables.

We just hit 20K stars for the Compound Engineering repo! github.com/EveryInc/compound…

Pretty impressive SEO for @every to show up as the first result when i simply google "every"

I would love to see data on the misspelling rate for prompts going into Claudex. Judging by my n-of-1, language is rapidly degrading/speciating

I bought Figma stock during the SaaSpocalypse panic. Talking to @mcolyer, Figma's director of product management for developers, made me wish I'd bought more. He joined me on @every's AI & I to make the case for a SaaS resurgence—and to explain why chat-based tools are the wrong interface for design. We get into: - Why running your own agents makes you more willing to pay for SaaS, not less - How Figma's MCP server allows you to approach design work from two directions: Take a live web page and reconstruct it on the Figma canvas, or hand a Figma design over to an agent so it can makes changes via pull request - The inherent limits of chat-based design, a format that isn’t equipped to generate lots of new ideas -Why review is the next bottleneck, and potential solutions for helping teams scale evaluations Watch below! Timestamps 0:01:03 - Introduction 0:02:15 - The SaaSpocalypse narrative has it backwards 0:05:27 - Matt’s email-agent origin story 0:13:21 - Divergent vs. convergent design thinking 0:17:39 - Figma’s MCP server 0:19:45 - Why design agents need personalization 0:22:09 - Every problem is a context problem 0:25:12 - Apple and Google as the reigning kings of context 0:28:18 - Why review is the new bottleneck

These are two of my favorite IRL people (who didn’t know each other!) and I’m beyond STOKED they got to chat

Shipping code and announcing it should be one workflow. New in compound-engineering: /ce-promote reads your PR and turns shipped work into copy-pasteable launch copy for X, LinkedIn, changelogs, and more. Even better: When @TrySpiral is connected, it writes the posts in your voice.

This perfectly encapsulates the mindset that every founder should have and every employee should have in their founder. So much win/win here, although if you’re a founder you know you have to fight a bit to make it happen

Your writing has a fingerprint. Stylometry is the science that measures it. We rebuilt Spiral's engine/brand around it. Drafts now sound like you 87% of the time. @TrySpiral has a new brand and a new engine.

Preach it @tedescau !

"Everyone two levels away from you, either up or down, is crazy"

Subscribe to @every and come to Compound Engineering Camp on Friday if you want to see how @kieranklaassen has reached agent orchestration nirvana

Codex thinks I'm a 7.5! Probably buttering me up for more tokens.

At @every, we've been supporting exec teams for a while. Those getting value from AI all run the same loop: 1- Get fluent: build something yourself first 2- Assign an owner 3- Automate one narrow, painful workflow (to start) 4- Build it to 95% (running evals & QA) 5- Scale the wins so other teams benefit It's slower saying you 'automated your company' but it actually works. Ultimately, implementing AI is all about the people. That's the best part!

Mine: 1. Claude Opus 4.8 1M xhigh fast 2. Codex GPT-5.5 high fast 3. Composer 2.5 fast 4. Gemini Pro 3.1

This is what surfing the Internet was actually like back then. You kids have no idea.