Your project is online — but is it any good? Today, two jobs. First, make it clear: rebuild your page so a total stranger gets it in five seconds and knows exactly what to do. Then trade pages with your group and tell each other the truth.
Second, work like an engineer: turn that feedback into issues, let AI ship each fix as a Pull Request, and review before you merge. One habit runs through all of it — read what your AI says. Don't look away the second it starts; read what it did and what it's asking you to do.
Every grey box is a prompt you can copy — drop it into Codex or Cursor. Keep this page open all class. Stuck? Mia is here. Homework: file 3 issues before you leave.
01 · Today
Part 1Make it clear, then trade feedbackRebuild your page so a first-time stranger gets it and can use it. Then open each other's sites in your group and say what's confusing.
Part 2Iterate like an engineerTurn feedback into issues, let AI ship each fix as a Pull Request, and review the change before you merge it live.
The ruleRead what your AI saysThe habit that runs through the whole class. When the AI stops, read what it did and what it wants you to do — before you touch anything.
HomeworkFile 3 issues todayEveryone leaves having written 3 GitHub issues — the feedback you got plus your own ideas, one specific task each.
02 · Make it clear to a stranger
You know what your project does — but a first-time visitor doesn't, and won't try hard to figure it out. The goal: someone who's never seen it should get what it's for and know how to use it. First prompt: have AI play an impatient stranger and walk your page, listing everything that's confusing, unclear where to click, or broken on a phone — then fix the worst of it.
请你扮演一个第一次打开我网站、还有点没耐心的陌生人——你不知道这个网站是干嘛的,也不想花力气研究。请你真的把我的网页从头到尾走一遍(先读我的 index.html,在浏览器里打开看),然后用大白话给我列三类问题:
① 看不懂:打开五秒内,我看不出这个网站是干嘛的、为什么我要用它,具体是哪里没讲清楚?
② 不知道点哪:我想用它,但不知道第一步该点什么、填什么,哪些按钮和步骤让人犹豫?
③ 手机上坏了:在手机这种窄屏幕上,有没有挤在一起、点不到、看不全、要左右拉的地方?
每一类都给我具体的、能动手改的清单(指出在页面哪个位置),别说空话。列完之后,挑最影响「陌生人一眼看懂」的几条,直接帮我改到 index.html 里,改完告诉我你改了哪些地方。
A wall of text is hard to read. Second prompt: have AI add simple images or icons so the page is easier to grasp at a glance — all pure front-end (SVG / emoji / CSS), and it tells you exactly where each one goes so you can swap them later.
Most people jump straight to "AI, build me the page" — and get back something that looks nothing like what they pictured, then burn time pushing it back and forth. Here's the upgrade: AI can now generate a real picture of your screen, not just describe one. Codex can call GPT image (gpt-image-1), you can use Doubao, or any other image generator you have on hand — whichever is handy. So have it draw an actual visual of the page first — the colors, the style, the layout. You pick and tweak the image until you like it, then hand that picture to Codex or Cursor and let it build the real page from it. You stay in control of what the thing ends up looking like.
我在做一个关于【一句话你的社会议题】的网页。先别写功能代码——请用 AI 生图(Codex 里的 GPT image,或者我用豆包等工具)帮我生成一张这个网页的界面设计图:风格是【在这里写你想要的风格,比如简洁、活泼、科技感】、配色【写你想要的主色调】、页面上要有哪些区块和按钮。先出图,我看顺眼、调好了再让你写代码。
TipFix it on the picture, not in the codeRecoloring one block or nudging a button is far faster on the generated picture than in code. Settle how it looks on the image first — don't rush into writing code.
这是我用 AI 生成、并挑好的界面图【把图贴在这里】。请照着这张图,用纯 HTML + CSS + JavaScript 把界面实现成一个真能打开的页面:布局、风格、配色都按图来,先把样子搭出来(具体交互功能可以先放占位,之后再加)。
The point: AI can really make pictures now — generate the visual, get it looking right, then let it write the code. That beats coding blind and reworking it ten times. Once the page is standing, you add the real features one at a time with the issue → PR → review loop from the rest of today's class.
04 · Trade pages, trade feedback
This is the heart of Part 1. Get into groups of 3–4 and open each other's live URLs on your own phone or laptop — be the stranger. Can you tell what it's for in one glance? Do you know how to use it? Where exactly do you get stuck? Say it out loud, be specific, and give every person at least one concrete suggestion. Write down the feedback you get — in a few minutes it becomes your issues.
LookOpen it cold, be the strangerOpen your groupmate's URL with zero explanation from them. First five seconds: do you get what it is, and do you know what to do?
SpeakBe specific, not just nice"I didn't get what this is", "I couldn't find where to click", "this looked broken on my phone." Say exactly where you got stuck — vague praise helps no one.
GiveOne concrete idea per personEveryone leaves each page owing the owner at least one thing they can actually change. No one gets skipped.
KeepWrite down what you hearJot down the feedback about your own page — you'll turn it into GitHub issues in the very next section. Don't trust your memory.
05 · Turn feedback into issues
Now Part 2 — work like an engineer. You've got a pile of feedback: from your group, plus your own ideas. Don't fix it all in one messy go. Break it into issues — one issue = one specific task. A repo full of clear issues is your to-do list, and it's how real teams keep track of what needs doing. Use AI to turn one piece of feedback into a clean issue and file it in your repo:
我刚做完同学互评,收到了一些关于我网站的反馈,自己也有一些想改的地方。请帮我把其中一条反馈整理成一个清晰的 GitHub issue,并直接建到我的仓库里。记住:一条 issue 只对应一个具体任务,别把好几件事堆在一起。
这条反馈是:<在这里写下你收到的一条具体反馈,比如「打开网站不知道这是干嘛的」>
请把它整理成包含三部分的 issue:
① 标题:一句话说清要解决的问题;
② 具体要改什么:用大白话说明现在是什么样、希望改成什么样、要改页面的哪个位置;
③ 怎么算改好了:列出能验证「这条做完了」的标准(比如「第一次打开的人五秒内能看出网站是干嘛的」)。
建好之后,把这个 issue 的链接发给我。我零基础,如果建 issue 需要我在 GitHub 上点哪里,一步一步告诉我。
06 · Let AI ship it as a PR
Now let AI actually do the work — but not by editing main directly. Have it open a Pull Request (PR): it makes the change on a new branch and bundles it as a proposal you can look at before it goes live. Why bother? Every change is recorded, you can see exactly what changed (the diff), and if something breaks you can roll it back.
One step before it's real: review. A PR is a proposal — read it before you accept it. Let AI (or the /review command in your tool) go over the diff and flag anything obviously wrong or half-done. Only once it's clean do you merge — and the moment you do, Vercel picks it up and deploys the new version automatically.
🔑 The one rule that saves you the most pain today, and it's free: don't look away the second your AI finishes. People lose twenty minutes right here, over and over. The AI didn't fail — it told you it needs you to do something, and nobody read it.
ReadIt's not done when it stops typingWhen the AI finishes, actually read what it says it did and what it changed. Don't just glance at the green checkmark and scroll on.
ActCatch the "your turn"Watch for lines like "go click Authorize in your browser" or "confirm this step before I continue." That's a task handed to you — not a bug.
CheckStuck is not the same as brokenBefore you panic that something's broken, scroll up and re-read the last thing the AI said. Nine times out of ten the answer is right there.
Build the habit today: when the AI stops, read first, then act. This single rule will save you more time this class than any prompt on this page. Whenever you feel stuck, the very first move is always the same — re-read what your AI just told you.
09 · Leave with
HomeworkFile 3 issues todayTurn the feedback from peer review plus your own ideas into 3 GitHub issues — one specific task each. Do this before you leave.
BonusShip one or two as PRsGot time and energy? Take an issue or two through the full loop: new branch → PR → review → merge → live.
Coming upSupabase, for the dataOnce everyone's research data is in, we'll come back and use Supabase to pool it all and analyze it. Not today — just so you know it's next.
10 · Before you go — class feedback
Two minutes, every class. Tell us what landed and what didn't — it directly shapes next week's class.
Generation AI · Class Reflection & Feedback
Two minutes — your feedback goes straight to the teacher and shapes the next class. Thanks!