I'm giving a workshop at @aiDotEngineer next week in SF. "Closing the Agentic Loop: Getting Agents to Safely Build, Verify, and Ship" It's gonna be great and I think there's still room if you want to apply to attend!

Typing every line yourself can hold up the fixes your users are waiting for. I talked with @kentcdodds on my podcast. Speed matters, and engineers still need to understand and stand behind the code they ship with agents. There's a blog post on this. Link in the first reply.

I'm announcing @ByteBinding, a modern EPUB editor that helps you make your ebooks the way you want them. 💅 WYSIWYG editing 🎨 Global and element styles 🔠 Custom fonts 🖥️ Windows, Linux, macOS support 📵 Fully offline 🎟️ One-time purchase Learn more:

can't wait to hear from @kentcdodds @alessio_joseph @theCTO @JakeKing @ayushsoni_io @TheCyclotron @jkudish @lucamaraschi @MichaelThiessen @yagudaev @shanni_talks @kimjune01 @ashaya @dmarticus @wyattjoh 🔥 need a tick? comment below, we basically at cap

we will need to rebuild and rewrite much of software to adapt to a new, faster pace. code used to arrive one drop at a time. soon, if not already, code will be written as if it were a continuous stream, like a violent river twisting and turning as it pleases. this is not a new thing: big tech cos have had to deal with this with the enormous scale of their engineering teams. but now ai has brought an incredibly elastic and capable workforce wielded by every engineer. this is your problem now, and the only way to adapt is to evolve your systems so agents - even and especially the ones with little context about the right way of doing things - can thrive. make the easy thing the right thing. your codebase is becoming organic architecture. agent contributions grow around the constraints and guardrails you’ve designed. good software engineering matters even more now! and no, the continuous stream of code is not something you have to watch helplessly. be more ambitious and design systems, frameworks, and languages to control the chaos. the time for mourning coding is long over

my grok bots (r&d, product, marketing) write their decisions into Kody by @kentcdodds. now when I open claude, cursor, or pi, it already has the context. no re-explaining. This is how I build puppi, solo with an AI team.

Nothing more validating than established products (that people love) copying your features. That's why you need to position your product away from their incentives. Do things that are against their best interest.

Working on a new feature in Kody called "profiles" which allows you/your agent to create a token/mcp connection that has a subset of permissions of your account's making things much more safe and auditable as well.

A: Uses AI coding agents HEAVILY in implementation and review and doesn't look at the code at all B: Hand writes and reviews everything Assuming the products solve the same problem etc, which product would you feel more comfortable trusting as a user?