Another often overlooked benefit of AI is how it makes it effortless to spin up solid user docs early in a product’s life. What used to be too time-intensive (And not worth the return) is now basically free, boosting conversion and stickiness early for your product.

It’s getting to the point where it feels like the UI in Cursor is changing daily. Absolutely love the product and work being put into it by the team but I’d really appreciate some consistency as well.

I love a good Year in Review as much as the next person, but not every app needs to do one, it's getting a little out of hand. I do not need to see my toaster’s 2025 highlights.

One of my favourite use cases with AI is to have it generate me a comprehensive manual testing checklist for my projects. It makes it a lot easier as a solo dev on a project to ensure you've tested everything imo.

Introducing Cowork: Claude Code for the rest of your work. Cowork lets you complete non-technical tasks much like how developers use Claude Code.

Real question before starting any new project these days: can this be vibe coded in an hour? I’m increasingly building quick solutions myself instead of hunting for tools. Depends on complexity for sure, but it’s happening a lot.

This is awesome and can confirm it works after trying it. It's yet another reason we don't always need insanely complex AI workflows to get solid results. Sometimes it just comes down to providing a little bit of extra context or guidance to the model.

Gemini 3 Pro with Google Antigravity does not get anywhere near enough love. It's easily the best combination I've seen to generate beautiful looking sites / dashboards in one shot. It will also use Nano Banana to generate assets as well. Highly recommend trying it out!

Tools that make marketing more accessible to devs are always a huge win in my book

Introducing Agentation: a visual feedback tool for agents. Available now: ~npm i agentation Click elements, add notes, copy markdown. Your agent gets element paths, selectors, positions, and everything else it needs to find and fix things. Link to full docs below ↓

x.com/i/article/2014…

📣 How we built the Codex agent loop Ever wonder what Codex does between your prompt and its response? Each turn assembles inputs, runs inference, executes tools, and feeds the results back into context until the loop ends openai.com/index/unrollin…

Introducing the Codex app—a powerful command center for building with agents. Now available on macOS. openai.com/codex/

My one complaint with GPT-5.3-Codex so far is it EATS tokens like crazy, especially compared to GPT-5.2-Codex on the same reasoning level. I am burning through usage in the Codex app at an alarming rate despite there being 2x limits until April. Still a 10/10 model though.

Introducing the Google Workspace CLI: github.com/googleworkspac… - built for humans and agents. Google Drive, Gmail, Calendar, and every Workspace API. 40+ agent skills included.

Automations are now GA. You can now: • Set the model and reasoning level • Choose if runs happen in a worktree or existing branch • Reuse workflows with templates Automations are great for recurring tasks — daily repo briefings, issue triage, PR comment follow-up, and more.

My absolute favourite combo lately has been OpenAI Developers Codex with Cursor Composer 2. They compliment each other well. Also feel like Composer 2 needs a shout out for how well it generates good looking UI fast.

We’re updating our ChatGPT Pro and Plus subscriptions to better support the growing use of Codex. We’re introducing a new $100/month Pro tier. This new tier offers 5x more Codex usage than Plus and is best for longer, high-effort Codex sessions. In ChatGPT, this new Pro tier

With GPT-5.5, Codex now gets more of the job done across the browser, files, docs, and your computer. We've expanded browser use so Codex can interact with web apps, and test flows, click through pages, capture screenshots, and iterate on what it sees until it completes the

You can now keep codex going for days. With GPT-5.5 it will build an entire OS kernel for you if you ask, or find critical bugs in a codebase, or optimize your database schemas, or… the options are endless.