Venus Chen
Pitching KiboTalk at the AdventureX booth Small steps make big changes. ♡
The club's first night stall, Qixi 2025

I have a soft spot for turning wild ideas into things that actually exist.

Venus / Ziyan Chen · 16 · ENFJ

Explore my work ↓

01 — Business Club

I didn't want to teach business only inside a classroom.

50+students in my elective
3real-world stalls
45.17%profit margin on our second flower sale
The seven-person crew after the Qixi 2026 flower sale
Qixi 2026 · 7 hours · 55 transactions

Inside the classroom

I run a year-long elective under the club's name — 40 minutes a week, taught by me, with 50+ students enrolled. It's not "listen to me lecture about business": every team lives through the birth of a product — find the problem, find the users, build it, figure out the business model, bring in AI, ship it, test it with real people, keep iterating — with Explorer / Builder / Product Owner roles in each group, ending in a Demo Day. Before class started I asked what they most wanted to learn. The notes came back: economics, AI coding, monopoly simulations — and one said "I want to learn all of it." I realized teaching people to build is itself a product: you have to hear what people actually want before deciding what to teach.

Teaching the vibe coding elective at the whiteboard

Outside the classroom

01 🌸 Qixi 2025 Our first stall ever Cost ¥415.9 · Profit ¥98 ↓ story & photos

Fresh flowers plus handmade beaded bracelets. The margin was modest, but for the first time the full loop ran end to end — sourcing, pricing, selling, counting the money, and splitting it under a written agreement.

The club's first stall on the street at night, Qixi 2025 Bracelets, flowers and the price board, Qixi 2025 The stall signboard on the night street, Qixi 2025
02 🌸 Qixi 2026 7 hours near Dongbai Center, Fuzhou Revenue ≈¥697 · 45.17% margin (target 30%) ↓ story & photos

Seven people split into departments — procurement, promotion, sales, finance — under a written profit-sharing plan. Over a hundred stems sold, one rotten rose left. What actually sold: single stems and flowers customers assembled on the spot.

Wheeling the flower cart through the night market, Qixi 2026 The flower cart with 6.6-yuan price boards, Qixi 2026
03 🔮 Sports Meet School flea market · tarot booth Cost ¥13.7 · Total profit ¥163.32 ↓ story & photos

For the third stall we changed the product entirely: tarot readings. Nearly zero cost — and proof that the same stall playbook works for an experience, not just for physical goods.

The tarot booth poster and deck at the flea market The tarot reading mat in action

The street had other ideas.

We planned
What actually happened
💐 Pre-designed bouquets
🌹 Single stems
🎮 Mini-games
❌ Almost nobody cared
📸 Polaroid add-on
❌ Didn't sell
💰 30% margin target
45.17% actual

The plan survived contact with the street for about an hour.

Sometimes I just want to make noise.

Aurora Band · 2025—present

The band I founded at school. First on stage in September 2025 — three school shows in nine months, from the freshman arts showcase to the summer concert.

On stage at the summer concert
3performances
6members
Venus — founder · piano / acoustic guitar / hulusi
SEP 2025Freshman Arts Showcase
DEC 2025New Year's Eve Gala
JUN 2026Summer Concert
2025.9.20Freshman Arts Showcase
Aurora Band group photo after the freshman arts showcase On stage performing at the arts showcase
2025.12.31New Year's Eve Gala
Performing at the New Year's Eve gala Rehearsing in the studio
2026.6.11Summer Concert
To the Summer concert program poster On stage at the summer concert

I started the band because I wanted to play on stage. Three performances later, I mostly remember the rehearsals.

03 — Things I built

I let AI write the code — but every product decision is mine.

I don't code in the traditional sense, but I love building products. I start from a problem I've run into myself: find the users, break down the need, design the flow — then vibe-code it into a website that actually opens. So far I've shipped several ideas for real. Some got used, some didn't; some are still going, some are paused. What I care about more and more is not "how many products I've made" — it's: once it exists, how do real people react?

EasyEcon

Live School pilot · ≈40 students

English practice and full mock exams for AP Micro students.

I finished AP Micro with a 5. What actually blocked me wasn't the economics — it was reading English questions and figuring out what they were really asking. So EasyEcon keeps the English originals and gives Chinese students scaffolding in Chinese context to understand them. I wrote the question bank, designed the flows and the mock-exam experience, and vibe-coded it into being. The mock mirrors the College Board Bluebook — timed MCQ and FRQ, with 2025 real papers. A one-page brief to our international-office director won a ~40-student Grade-10 pilot this term. What I want to know now is no longer "can it be built" — it's: will they actually finish a full mock exam, and come back for a second?

An English MCQ in EasyEcon with colored answer options EasyEcon knowledge points with Chinese scaffolding for English terms
easyecon.lovable.app ↗

KiboTalk

Most Sincere Award AdventureX 2026

What we wanted to solve wasn't "can't speak English" — it's "when something actually happens, I don't know what to say."

On a four-person team I owned product direction and user scenarios, plus the pitch narrative and visual assets. Instead of yet another vocab app or AI chatbot, we put the scenarios inside high-pressure real conversations — interviews, service counters — where you face a "person" who actually pushes back. Online you use the app; in-person it can pair with AR glasses for live translation and answer cues — the hardware is never required. AdventureX 2026 had ≈8,975 applicants and 800 on site; we won the Ant Group Lingguang track's "Most Sincere Award" (¥2,000 team prize). It was the first time I clearly realized: no matter how beautifully a product is pitched, without a real person and a real scenario, it's still just a PowerPoint.

The Ant Group Lingguang track Most Sincere Award for KiboTalk The KiboTalk app running a store-clerk conversation practice Pitching KiboTalk to visitors at the AdventureX booth The four-person KiboTalk team at AdventureX

PromptSpeak

Paused 32 users

My first product: an AI IELTS Speaking mock exam with scoring.

In September 2025, just starting to learn vibe coding, I built the IELTS Speaking tool I wished existed — full Part 1 / 2 / 3 mock exams and scoring, in a flow close to the real test. It really shipped, and real people really used it — about 32. But "can be built" and "worth continuing" turned out to be two different things: acquisition was too expensive and competitors were already strong, so I paused. It was the first time I truly felt, from inside my own product: a product can be pretty good and still not deserve to continue.

PromptSpeak scoring a mock answer: Band 7.5 overall The PromptSpeak sign-in screen
promptspeak.space ↗

HungMan

Live First real user story

An English hangman game a junior actually used to memorize vocabulary.

After finishing it, I just sent the link to a junior from school. She actually used it to study for a while and told me: "it's way less painful than rote memorization." She also had one very specific request: custom wordlists should show Chinese meanings. It might be the smallest piece of product feedback I've ever received — and the one that made me happiest. Because in that moment, for the first time, I concretely felt: what I make is no longer just "my work" — it's starting to become someone else's tool.

HungMan gameplay: guess the English word before the drawing completes HungMan word-library picker with IELTS and TOEFL lists A missed word turns into a learning moment with meaning and example The junior's chat feedback: easier than rote memorization
hangman-english.pages.dev ↗

Quanzhou Heritage Runner

Just for fun

A little game I made for fun: Quanzhou's intangible heritage stuffed into a vertical pixel runner.

It was my first attempt at making a game. No business plan, no funding story — I just wondered: if Quanzhou's heritage could become a game you play while running, wouldn't that be interesting? In the end I shipped it with a Xiaohongshu small-tools pack, and tried for the first time to design a product for a content platform instead of an app store.

Pixel-art running through Quanzhou heritage scenes Character skins based on Quanzhou intangible heritage