A Junior Who Can't Code Used AI to Scrape 88 Data Points and Built an App in 3 Days

Xiao Lin can't code. But she used AI to scrape 88 emotional data points and built an app in 3 days.

She studies Digital Media, not Computer Science. Web scraping, APIs, data analysis—she knows none of them. By traditional standards, she'd need to learn Python for half a year first.

But she said just one sentence, and 3 minutes later, 88 real emotional data points were lying in front of her.

ONE   One Sentence, 88 Data Points

Xiao Lin wanted to build an emotion management app, but she didn't know what people's actual emotional pain points were. Sending surveys was too slow, and interviews had too small a sample size. She needed large-scale real data.

So she said one sentence to WorkBuddy:

"Search Xiaohongshu posts from the past week, with keywords including 'grad school anxiety,' 'high work pressure,' 'breakup loneliness,' and 'anxious internal friction.' Scrape post content and comments, categorize them into four dimensions: study, work, relationships, and family, and extract emotion tags."

She went to pour a glass of water. When she came back, 88 data points were listed on the screen.

Each data point included title, body text, comment count, like count, publication time, and IP location. The AI automatically tagged emotions—anxiety, fatigue, loneliness, internal friction, insomnia.

They were categorized into four themes: 20 study-related, 20 work-related, 20 relationship-related, and 28 mental exhaustion-related.

                                                                         Figure 1: From one sentence to 88 data points in 3 minutes

TWO   Three Discoveries That Gave Her Chills

Xiao Lin thought she understood "anxiety." The data told her she was wrong.

Discovery 1: She thought "internal friction" was unique to students, but the data showed grad school applicants, office workers, and housewives were all talking about the same thing. It wasn't exclusive to one group; it was a universal problem.

Discovery 2: She thought late-night posting peaked, but the data showed the peak for emotional posts was between 7 AM and 9 AM. People weren't breaking down at night; they felt the heaviest sense of helplessness upon waking in the morning.

Discovery 3: IP locations concentrated in Tier 1 and 2 cities, with Beijing, Shanghai, Guangzhou, and Shenzhen accounting for about 60%. This meant the early version of the app should focus on young professionals and exam candidates, not general users.

These three discoveries directly changed her app's feature priorities. The "Break Internal Friction Patterns" feature, originally ranked last, was moved to the highest priority.

THREE   AI Helps You Go from 0 to 1, But You Must Walk from 1 to 100 Yourself

With the data, Xiao Lin asked AI for the next step:

"Based on these 88 emotional data points, help me analyze: 1. What are the most frequent user emotions? 2. What are the most common trigger scenarios for each emotion? 3. Based on the analysis, design 5 core features for my app."

The AI's feature suggestions were chillingly accurate—not because they were profound, but because it truly understood what lay behind those emotions.

For example, it suggested adding an "Emotion Check-in" feature: not writing a diary, but selecting an emoji every time you open the app. After 7 consecutive days, it generates an emotional fluctuation chart. Because the data showed that anxious people don't need advice most; they need to see their own emotional patterns.

But there were three things AI couldn't do.

First, she had to judge which data was valuable herself. AI handles classification, not insight. The judgment that "mental exhaustion is a cross-group universal pain point" was hers alone.

Second, she had to decide the app's direction herself. AI suggested 5 features, but choosing which ones, prioritizing them, and designing the UI were all her decisions. AI is an advisor, not a decision-maker.

Third, she had to talk to users herself. Data tells you "what," but not "why." Why do grad school applicants post "I can't take it anymore" at midnight? The answer only comes from talking to real people.

AI helped her go from 0 to 1. The path from 1 to 100 must be walked by herself.

                                                                   Figure 2