Started from real user pain points to turn a single-point bookkeeping tool into a complete three-role management mini-program
Requirement discovery: observed the family seedling farm's "11 greenhouses, 264 beds" where seedling ages were mentally calculated, orders hand-written, and shipping fully manual — pinpointing the two pain points of efficiency and errors.
Requirement breakdown: decomposed into three-role permissions, greenhouse visualization, seedling-age back-calculation, AI bookkeeping/order recognition, order scheduling and auto-reminders, prioritized and shipped in phases.
Validation & iteration: AI parsing accuracy 95%+, bookkeeping 2h→30min; error feedback (corrections) makes parsing more accurate over time.
Defined the problem from 0: identified repetitive labor in long-content knowledge reuse, and designed a four-stage AI workflow — extract → reuse → draft → fact-check.
Independently produced requirement definition, PRD, system architecture, a runnable prototype and product demo — the full "problem → solution → validation" loop.
Independently produced a 12-page product proposal + pitch script and presented live, translating technical solutions into business-friendly language.
Broke "job hunting" into three steps — JD analysis → résumé tailoring → AI mock interview — and built them into an integrated product, available online.
Drove feature design with real job-hunting needs, quickly validating the product value of "AI helping with career decisions".
Keywords Product Design · Rapid Prototyping · User Scenarios · AI Applications
High School Physics One-on-One Tutoring | Teaching & CommunicationTutor · One-on-one2 年
Two years of one-on-one tutoring covering all high school grades, forming a "diagnose → explain → practice → feedback" closed-loop teaching method.
Able to break abstract concepts into language students understand, training requirement understanding and empathetic communication — core soft skills of a product manager.
Keywords Learning Diagnosis · Concept Breakdown · Communication & Empathy
Internship
Tianxing Technology | Embodied AI Intern2026.07 – 2026.08
Ran the full SO101 robotic arm ACT model inference & control pipeline, and rewrote the debugging docs.
Smart Agriculture Research Institute | Data Annotation Intern2026.01 – 2026.02
Completed ~4000 annotation points/day at 95%+ accuracy, understanding AI model quality from the data side.
Education
Tianjin Normal UniversitySoftware Engineering | Bachelor2024 – 2028
Academic Performance: Year 1 GPA rank 16/50, comprehensive rank 7/50; Year 2 GPA rank 13/50, comprehensive rank 9/50 (top 20% overall); school scholarship for two consecutive years