Learn By Doing With Steven

Tricks About Vibe Coding and Updates On Recent Projects

https://open.substack.com/pub/steven923044/p/tricks-about-vibe-coding-and-updates?utm_campaign=post-expanded-share&utm_medium=web Substack link is will multimedia.

Glad to see you here again. Here is a quick review about my projects and vibe coding, I hope they could somehow be useful for you.

Podcast

Although I still welcome new guests to join my podcast Steven Data Talk, unfortunately recent invites all got put aside somehow, so the next thing I will do would probably focus more on projects.

Videos

About my videos, the Chinese version of stanford startup course distillation, Vibe coding personal youtube learning companion, etc, will be recorded and published.

Writings

About my writings, all will go on on wechat public account, substack, linkedin, etc. The focus would be leading learning resources like IBM, different VCs’ channels, and maybe the next ones could cover some deep dive of podcast like lex, dwarkesh, or review of leading AI field courses like Stanford ones.

Vibe Coding(more than 80% of the code is written by AI)

For the past two months, I have been coding with antigravity. First of all, the free quota of tokens is generous. Second, I am really picky on AI related products now, since my first question is always, why should not I build one.

Here are some quick notes for your reference:

  1. Starting from your own use case then bootstrappingly test your idea, is much better than theory first then implementation first.

  2. Good documentation habbit does matter for fresh start over and summarization of periodical work progresses.

  3. Do it yourself, and forget about those fancy apps claimed to be optimal. The market is full of noise and I prefer to build my own apps, programming will be a tool instead of an expertise. And additional learning on SOTA SWE is recommended for sure, where SWE, SWE with agentic tooling, non SWE coders, will have difference nontheless but the tool has become easier to access and more helpful than before.

  4. Antigravity + claude + Gemini3 have inspired me different chunking strategies(more than chunking size, and for small length articles full context injection could be more useful, etc), mixture of search algorithm beyond simple rag and similarity ranking, etc. This really helps me speed up the development practice and learning.

  5. Do not ignore the risk and guardrails etc, if you saw my previous pubblications, I do always focus on many security aspects about coding, etc. So most of the apps to be mentioned below will work fine in local device with small model, but to further deploy in more complexed enviroment, prudence is required and optimization of algorithms is necessary.

Some notable projects are as below, and some will become opensource once I am confident that they would be beneficial for everyone:

  1. Updated github io page

  2. Personal learning HUB

  3. Escavator Sales Engine

  4. Industry Dashboards - Industrial Machinery Pulse

  5. Financial Analyst

  6. Wechat Public Account article viewer and chat bot

  7. Other notable projects

  8. Conclusion

  9. Updated github io page

It has become a bubby to every now and then ask the agentic ide impress me with new designs. Codex could provide some improvements but it seemed to be limited since I always use the free version so the model might be the low version of chatgpt. With previsouly used windsurf, the experience was positive. Now with antigravity, and mcp or chrome link to check ui ux instantly, the whole development feeling has changed.

Additionally, like this version you see below, I even incorporated manus AI in the process, and got suprised by the item arrangements and drop down design. So, mixture of AI experts sometimes could be useful.

  1. Personal learning HUB

If you already know some youtube channel(like the below case, I use mine; and in a more serious sence, if you use the channels not owned by you, read the permission of each media to make sure if you can go beyond personal study usage) and you want to build knowledge graph, vector db and rag chat, it is not so hard now even if you might find coding task not suitable for you.

With agenti ide or vibe coding tools, even non code tools(like prev langflow was one of the tools I used, before IBM acquisition), you can build your app easily. In my case I leveraged both claude and gemini latest models to code, and the result is beyond expectation. However, security, readability, agentic workflow error, etc, are still some aspects we need to pay attention to and, do not deploy the apps to production without professional review.

Besides, I customized other different learning apps. Below are some highlights about knowledge graphs.

  1. Escavator Sales Engine

Automation of industrial machine sales support is crucial to speed up the sales procedure, which is highly welcomed by different sales teams I talked with.

This could have been a project for my potential employer but it now becomes my side project.

  1. Industry Dashboards - Industrial Machinery Pulse

Different industrial machine sales teams in Europe want to improve the data dashboards, standard sales document automation. At the moment the below demos are close to industry adoption level, and the up scale SWE redesign could immediately push the projects to production. They are waiting to be opensource codes when they reach a mature level. Some features are as below for quick preview.

  1. Financial Analyst

A rag chatbot analyzing the Zhipu IPO prospectus. And for Minimax case, I used antigravity to separate, organize, process the chapters directly, this could be another way to fast disect contents.

  1. Wechat Public Account article viewer and chat bot

This could have been put in the category of learning hub but it focuses on the channel where I published most articles. So I might find it unique in general.

  1. Other notable projects

Banking AML workflow simulation with LLM backend enhanced screening and structured data processing pipline.

Medical industry financial assistant working on deciphying global accounting standards and improvements of accounting efficiency.

Countless language learner, games, in google ai studio.

Some of my old videos+youtube repo are still useful, feel free to check out on my youtube channel and github.

And more.

  1. Conclusion

For any enterprise, you need mixture of capability experts. Which means, hiring an entire QWEN team won’t save your business. Developing models is one thing, demoing GenAI app is another, deploying GenAI tech at certain range is yet another, then scaling up the usage is another story.

But, hiring and collaborating with professionals with profound knowledge of the industry, with digital+GenAI craftsmanship, will surely make a huge difference.

I have not written some evaluation metrics above, but surely I can add in documentations in later stages. But in short, with AI tools(frontier lab products+agentic ide+additional tools) will elevate personal capability to another level. If I were to start a new business, I can quickly bootstrap with no hastle to hire or getting finance.

In addition, I am open for collaborations, contacts as below.

Learn by Doing with Steven 数能生智 | 社媒矩阵 📅 预约交流 | Book a Call 平台

链接

🗓️ Cal.com

https://cal.com/stevenwang

📅 Google Calendar

https://calendar.app.google/fT6ip6i638AGuP8v5

📬 ChiliPiper

https://gmail.chilipiper.com/me/steven-wang

⏰ Calendly

https://calendly.com/steven_wang/60min

🌐 主站与文章 | Website & Writing 平台

链接

🧱 Github

https://github.com/learnbydoingwithsteven

🌐 Github.io

https://learnbydoingwithsteven.github.io/

🐻 Bear Blog

https://learnbydoingwithsteven.bearblog.dev/

✍️ Substack

‍

https://substack.com/@steven923044‍

‍‍✍️ Substack(AI)

https://substack.com/@learnbydoingwithsteven

📰 LinkedIn Newsletter

https://www.linkedin.com/newsletters/7283566848875384833/

📲 微信公众号

https://mp.weixin.qq.com/s/_UgwPOKp0KFDNQdPSYuWMg

💬 社群矩阵 | Communities 社群

链接

🌐 LinkedIn Group（中/欧/美AI社群）

https://www.linkedin.com/groups/15054015

💬 Discord（中欧美AI社群）

https://discord.gg/XE6WpAfM

💬 Discord（Learn By Doing）

https://discord.gg/47yq8KcC

📡 Telegram Group（技术·播客）

https://t.me/+i9NRjGCKjRQxMDNk

📱 WhatsApp Group（技术·播客）

https://chat.whatsapp.com/Gmfju4artZB0VfRxV93H8p

🧑‍💼 直接联系 | Direct Contacts 项目

Email

Career / Banking / Finance / GenAI / DataScience / Industry / Consulting and Collaborations

wjbear2020@gmail.com

💰 支持创作 | Support Steven’s Work 平台

链接

💳 Paypal

https://www.paypal.com/paypalme/wangjiansuper?country.x=IT&locale.x=en_US

☕ Buy Me A Coffee

https://buymeacoffee.com/learnbydoing

🎥 视频矩阵 | Video 平台

链接

▶️ YouTube Learn By Doing With Steven

https://www.youtube.com/@learnbydoingwithsteven

▶️ 数能生智（中文频道）

https://www.youtube.com/@%E6%95%B0%E8%83%BD%E7%94%9F%E6%99%BA

🎵 TikTok‍

https://www.tiktok.com/@learnbydoingwithsteven‍‍

📺 哔哩哔哩（Steven数据漫谈）

‍‍

https://space.bilibili.com/3546784399886498?spm_id_from=333.788.upinfo.head.click‍‍

🎵 抖音

https://www.douyin.com/user/self?modal_id=7577406098097933622&showTab=post

🌍 网站 / 频道 / 平台 | Website 平台

链接

WhatsApp Channel

https://whatsapp.com/channel/0029VazqfKFK0IBoyfgyO70b

Telegram Channel

https://t.me/learnbydoingwithsteven

Github

https://github.com/learnbydoingwithsteven

Github.io‍

https://learnbydoingwithsteven.github.io/

LinkedIn Newsletter(Business)

https://www.linkedin.com/build-relation/newsletter-follow?entityUrn=7359504834644926464

LinkedIn Newsletter(Tech)

https://www.linkedin.com/build-relation/newsletter-follow?entityUrn=7283566848875384833

Substack

https://substack.com/@steven923044

Bear Blog

https://learnbydoingwithsteven.bearblog.dev/

微信公众号

世界模型的下一站：李飞飞团队World Labs如何定义“空间智能”新赛道？

📱 社交平台 | Social 平台

链接

小红书

https://www.xiaohongshu.com/user/profile/5e0e450b0000000001001e26?xsec_token=YBolHet_ed8Npv1I7yr4lMGb6VRZWtbkE9QSkodxdCu0I=&xsec_source=app_share&xhsshare=CopyLink&appuid=5e0e450b0000000001001e26&apptime=1737132065&share_id=c4262bd995c34cebaab2e0d85e5a3875

LinkedIn（独立项目）

https://www.linkedin.com/in/steven-w-6828a31bb/

LinkedIn（完整职业）

https://www.linkedin.com/in/jian-w-83bb36440/

X（Twitter）

https://x.com/Catchingtides

Facebook

https://www.facebook.com/profile.php?id=61571798756202

Instagram

learnbydoingwithsteven

🤝 合作伙伴 | Collaborations 合作方

链接

Vanta Tech Lab

https://www.linkedin.com/company/vantatechlab

DukeCEO

https://www.linkedin.com/company/chinese-entrepreneurs-organization-at-duke-dukeceo

创·见 Founder Vision

https://www.xiaoyuzhoufm.com/podcast/66a322470736bb4045362844?s=eyJ1IjoiNjVkZDlhNDBlZGNlNjcxMDRhOThhNjZkIiwiZCI6MX0=

我作为嘉宾的节目

https://www.xiaoyuzhoufm.com/episode/690c8ad5d99642be96c4accc

🚗 兴趣爱好 | Hobby 内容

链接

Steven On The Road (YouTube)

https://youtube.com/@stevenontheroad6129?si=pAUvAm0af6eFJrDn

Steven On The Road（哔哩哔哩）

https://space.bilibili.com/157133040

Learn by Doing with Steven 数能生智 | 播客矩阵

  1. Steven Data Talk “Steven Data Talk” — delivering the clearest conversations on cutting-edge AI, technology, innovation, business, and entrepreneurship.

Now available on Spotify, Apple Podcasts, YouTube, Amazon Music, Xiaoyuzhou, Ximalaya, and more.

Support the creator & explore all links:

https://linktr.ee/learnbydoingwithsteven

平台

链接

Apple Podcasts

Spotify

喜马拉雅

https://www.ximalaya.com/album/88884765

小宇宙

https://www.xiaoyuzhoufm.com/podcast/68ef81ce0a78e59c5c5c45e7

YouTube Music

https://music.youtube.com/playlist?list=PLfV0OO4XXVBk1oCeZg-xwdnYbNuSDqgmW&si=EQtgt96FfSZSwxvc

Amazon Music

https://music.amazon.com/podcasts/b31ecf00-32e8-41b5-96cd-13e86253d249/steven-data-talk

  1. Steven 数据漫谈 《Steven数据漫谈》——用最清晰的方式，聊最前沿的人工智能、科技、创新、商业、创业思考。现已登陆 Spotify、Apple Podcasts、YouTube、Amazon Music、小宇宙、喜马拉雅 等平台。

所有链接，支持作者：https://linktr.ee/learnbydoingwithsteven

平台

链接

Apple Podcasts

Spotify

喜马拉雅

https://www.ximalaya.com/album/89574928

小宇宙

https://www.xiaoyuzhoufm.com/podcast/68ef81d14ce3619b345a32b2

YouTube Music

https://music.youtube.com/playlist?list=PLfV0OO4XXVBmQOOLxMpZXn519_PW3uneG&si=rgCVgHICnqNK5rFX

Amazon Music

https://music.amazon.com/podcasts/6d68d8c4-d7bb-4c1d-8b6c-1e9b0946463d/steven%E6%95%B0%E6%8D%AE%E6%BC%AB%E8%B0%88

  1. Steven AI Talk（多语） “Steven AI Talk” — delivering the clearest conversations on cutting-edge AI, technology, innovation, business, and entrepreneurship with AI summarizations on various high quality source contents.

🔗 Support the Creator & Access All Links

⁠https://linktr.ee/learnbydoingwithsteven⁠

语言

平台

链接

English

Apple Podcasts

English

Spotify

English

Amazon Music

https://music.amazon.com/podcasts/7aaf0f86-7cb1-4f6f-bba3-6fd3cb9dcad2/steven-ai-talkenglish

English

小宇宙

https://www.xiaoyuzhoufm.com/podcast/68ef7ec2332567e348b6e57b

English

YouTube Music

https://music.youtube.com/playlist?list=PLfV0OO4XXVBk811V6mTVbL483S_56ZtF5&si=qqGM8Es0NTSFtflX

中文

Spotify（Steven AI 播客）

中文

喜马拉雅

https://www.ximalaya.com/album/88276097

Italiano

Spotify（Italiano）

  1. YC 斯坦福创业课 2015 CS183B 精讲 平台

链接

Apple Podcasts

Spotify

喜马拉雅

https://m.ximalaya.com/album/109171033?from=pc

小宇宙

https://www.xiaoyuzhoufm.com/podcast/68ef7ec662e8bfe0dffdd116

YouTube Music

https://music.youtube.com/playlist?list=PLfV0OO4XXVBlRgHAHArWBcpbOYykZfMqI&si=KwnQAp25yoprI39H

Amazon Music

https://music.amazon.com/podcasts/97f55ca2-d30d-48d8-afa5-9d51362bf92c/yc%E6%96%AF%E5%9D%A6%E7%A6%8F%E5%88%9B%E4%B8%9A%E8%AF%BE2015cs183b%E7%B2%BE%E8%AE%B2

通用免责声明Disclaimer