Mersall retuiteado
Mersall
2K posts
Mersall
@AMersall
tech lead obsessed with AI coding workflows. building haac-aikit — the cross-tool layer for claude, cursor, copilot & co.
Se unió Nisan 2013
735 Siguiendo243 Seguidores
Mersall retuiteado
Slack now renders HTML attachments instead of just showing it as text 😭🙏
Thariq@trq212
my one Slack feature request- don't preview HTML as a scary text blob, I find myself wanting to sending coworkers HTML files that Claude generates pretty often, but the click through rate is horrendous
English
Mersall retuiteado
شغلى فى الlocalization خلى عندى OCD. مثلا فى ألمانيا علامة اليورو بتبقى بعد السعر €14 بينما فى الدولار بتبقى قبله 15$ ، وفى هولندا عكس ألمانيا بتبقى قبل السعر 14€. فروقات تافهة بس بتفرق فى ثقة المستخدم وإلا مخه بيحس إن فى حاجة غلط.
العربية
Mersall retuiteado
Mersall retuiteado
Built HAAC-AITKit because I got tired of every developer using AI differently and getting different results.
One CLI command installs the same rules/config across AI agents so teams stay consistent.
1500+ downloads first week 🚀
hamad-center.github.io/haac-aikit/
English
@HilaShmuel Yes it’s amazing u can yes haac-aikit package for it and more
English
Coolest thing is when your app docs look and feel like the app itself.
docs.runcabinet.com is live 🗄️🥳
English
AI 写出来的技术文档动辄几千字，全在终端里滚，没人愿意看。md2html 让 AI 自动把这些 Markdown 转成带侧边栏目录、图表、时间线、卡片和警告框的 HTML 页面，一个文件就能发给团队看。
github.com/haidang1810/md…
中文
Cross-team alignment used to be a nightmare. Not anymore. ❌
Imagine any AI tool using the same skills, rules, and commands for the exact same results. This is a massive workflow revolution. 🚀
👇 Check it out here: hamad-center.github.io/haac-aikit/
#AI #CrossTeam
English
これ便利すぎる。
海外で話題のやり方で、Claudeに「このアプリ全体を、1枚のHTMLと1つのJSONにまとめて」と頼むだけで、複雑なシステムをわかりやすく可視化できる。
・いまの設計が“見える化”されて、頭の中の地図ができる
・人間が読む用はHTML、次のチャットや新しい作業をする相手用はJSON…役割が分かれてる
・コードベースが「自分で説明してくれる」状態になる
続きで、そもそも何が起きてるのかを噛み砕いて書く👇
日本語
tired of AI building screens that look nothing like your homepage?
/design just shipped in haac-aikit 0.13
one DESIGN.md every AI tool reads first. interactive HTML showroom for live tweaks.
+25pp over freestyle (93% vs 68% in benchmark).
hamad-center.github.io/haac-aikit/
English
Claude Code users are quietly switching from Markdown to HTML.
Specs, PR reviews, reports, prototypes, editors.
HTML is becoming the new agent artifact.
Bookmark this.
Thariq@trq212
English
I struggle to understand anything without a proper visualization
In Copile, you can ask agents to build HTML visual explainers right on the canvas, instead of opening it in browser tabs
Easy to revisit, edit, and share
Andrej Karpathy@karpathy
This works really well btw, at the end of your query ask your LLM to "structure your response as HTML", then view the generated file in your browser. I've also had some success asking the LLM to present its output as slideshows, etc. More generally, imo audio is the human-preferred input to AIs but vision (images/animations/video) is the preferred output from them. Around a ~third of our brains are a massively parallel processor dedicated to vision, it is the 10-lane superhighway of information into brain. As AI improves, I think we'll see a progression that takes advantage: 1) raw text (hard/effortful to read) 2) markdown (bold, italic, headings, tables, a bit easier on the eyes) <-- current default 3) HTML (still procedural with underlying code, but a lot more flexibility on the graphics, layout, even interactivity) <-- early but forming new good default ...4,5,6,... n) interactive neural videos/simulations Imo the extrapolation (though the technology doesn't exist just yet) ends in some kind of interactive videos generated directly by a diffusion neural net. Many open questions as to how exact/procedural "Software 1.0" artifacts (e.g. interactive simulations) may be woven together with neural artifacts (diffusion grids), but generally something in the direction of the recently viral x.com/zan2434/status… There are also improvements necessary and pending at the input. Audio nor text nor video alone are not enough, e.g. I feel a need to point/gesture to things on the screen, similar to all the things you would do with a person physically next to you and your computer screen. TLDR The input/output mind meld between humans and AIs is ongoing and there is a lot of work to do and significant progress to be made, way before jumping all the way into neuralink-esque BCIs and all that. For what's worth exploring at the current stage, hot tip try ask for HTML.
English
HTML Artifacts are a big part of how I work with agents now.
Artifacts can be more than just static files.
When combined with agents, they can take action or help you take action.
This unlocks all kinds of interesting ways to work with agents.
This is clearly the future.
Check out this writing and scheduler artifact I built in a few minutes.
It uses a bit of HTML and JS.
All the data is in markdown (Obsidian vaults), so the agent can access and modify it at any time. No DB needed. No sophisticated functionalities. The agent decides all that for me based on the skills, context, and memory it has access to.
The best part about this simple stack is that all the important information stays with me. This has allowed me to build a recursive self-improving system and automations that can better tap into coding agents like Codex or Claude Code.
I could have paid or built an entire app for scheduling posts, and there are so many of them out there. But I don't need to. I've realized a simple artifact does the job. And the simplicity of it is actually an advantage. Very little maintenance for very high returns on personalization, time, and efficiency.
The other benefit of this is that I can add features as I please. That level of personalization feels magical, and we should all be pursuing more of it.
All of this just keeps compounding.
Of course, this example is just about writing. But I have similar artifacts for research, design, experimentation, evaluation, and so much more.
And no, I didn't actually publish the post example I shared in the clip. It was just for demonstration purposes. I actually spend more time than this when writing together with agents.
Lastly, having built my own agent orchestrator tool has made me realize that simplifying the tool stack is a superpower.
If you are curious about how all this works, I will do a live session next week: academy.dair.ai/events/cmovobp…
English