惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Apple Machine Learning Research
Apple Machine Learning Research
博客园_首页
G
Google Developers Blog
aimingoo的专栏
aimingoo的专栏
罗磊的独立博客
博客园 - 【当耐特】
M
MIT News - Artificial intelligence
D
Docker
博客园 - 三生石上(FineUI控件)
博客园 - 司徒正美
人人都是产品经理
人人都是产品经理
博客园 - 叶小钗
月光博客
月光博客
S
SegmentFault 最新的问题
Jina AI
Jina AI
Blog — PlanetScale
Blog — PlanetScale
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
博客园 - Franky
L
LangChain Blog
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
Microsoft Azure Blog
Microsoft Azure Blog
阮一峰的网络日志
阮一峰的网络日志
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
Last Week in AI
Last Week in AI

DEV Community

Authentication Security Deep Dive: From Brute Force to Salted Hashing (With Java Examples) Why AI Systems Don’t Fail — They Drift Spilling beans for how i learn for exam😁"Reinforcement Learning Cheat Sheet" I Replaced Chrome with Safari for AI Browser Automation. Here's What Broke (and What Finally Worked) How Python Borrows Other People's Work The $40 Architecture: Processing 1 Billion API Requests with 99.99% Uptime Vibe Coding: A Workflow Guide (From Zero to SaaS) Most webhook security guides protect the wrong side. The scary part is delivery. Headless CMS for TanStack Start: Build a Blog with Cosmic EU Age Verification App "Hacked in 2 Minutes" — What Actually Happened Comfy Cloud’s delete function does not actually remove files Running AI Models on GPU Cloud Servers: A Beginner Guide Event-driven media intelligence with AWS Step Functions and Bedrock I scored 500 AI prompts across 8 quality dimensions — here's what broke How to Call Google Gemini API from Next.js (Free Tier, No Backend Needed) The Portal Protocol: Reclaiming Human Connection in the Age of AI How to Fix Your Team's Scattered Knowledge Problem With a Self-Hosted Forum Intro to tc Cloud Functors: A Graph-First Mental Model for the Modern Cloud Designing Multi-Tenant Backends With Both Ownership and Team Access I Built a Neumorphic CSS Library with 77+ Components — Here's What I Learned PostgreSQL Performance Optimization: Why Connection Pooling Is Critical at Scale Cómo construí un SaaS multi-rubro para gestionar expensas en Argentina con FastAPI + Vue 3 🚀 I Built an Ethical Hacking Scanner Tool – Open Source Project I Replaced /usage and /context in Claude Code With a Single Statusline A Pythonic Way to Handle Emails (IMAP/SMTP) with Auto-Discovery and AI-Ready Design I Collected 8.9 Million Polymarket Price Points — Here's What I Found About How Markets Really Move EcoTrack AI — Carbon Footprint Tracker & Dashboard Everyone's Using AI. No One Agrees How. 5 self-hosted ebook managers worth trying in 2026 Building Your First AI Agent with LangChain: From Chatbot to Autonomous Assistant
Interview Tree: Turning User Interview Transcripts into S...
Isaiah Kim · 2026-06-14 · via DEV Community
Cover image for Interview Tree: Turning User Interview Transcripts into Structured Opportunity Trees with Claude

Isaiah Kim

I built Interview Tree because synthesizing user interview transcripts by hand is slow and error-prone. Reading through long conversations to find recurring problems, group themes, and pull supporting quotes takes hours. I wanted to see if Claude could do that extraction reliably enough to be useful in a real research workflow.

What it does

Paste any user interview transcript into the editor, hit analyze, and the app returns a structured opportunity tree: a hierarchy of problems, themes nested under each problem, and verbatim quotes from the participant anchored to each theme. The output renders as a collapsible, depth-indented, color-coded tree you can explore at every level.

Every theme is backed by exact quotes — not summaries or paraphrases — so you can see what the participant actually said rather than what the model inferred. There's also a sample transcript preloaded if you want to explore the output immediately without any data of your own.

How it works

The app is a Next.js 16 / React 19 frontend with a server-side API route that handles the Claude call. When you submit a transcript, the route sends it to claude-sonnet-4-6 via the Anthropic SDK with a prompt that asks for a specific typed JSON structure. Claude returns that structure — problems, themes, quotes — and the frontend renders it recursively into the tree UI.

Using typed, validated JSON as the intermediate format means the tree renders consistently every time. There's no brittle parsing of prose output.

The UI is built with Tailwind CSS, shadcn/ui components, and Novus by Pendo. The whole thing deploys on Vercel.

How I built it

This was a hackathon project. I used Claude Code — Anthropic's agentic coding tool — to generate and iterate on the codebase throughout the build. Claude Code handled the Next.js scaffold, the API route logic, the recursive tree rendering, and the Tailwind styling. The in-product AI is a separate Claude API call (claude-sonnet-4-6) running server-side — distinct from the tooling used to write the code.

Try it

Stack: Claude API · Next.js 16 · React 19 · Tailwind CSS · shadcn/ui · Novus by Pendo · Vercel