AI-Powered Resumes with Super People & Weaviate

Weaviate vector database · Intermediate ·🔍 RAG & Vector Search ·7mo ago
Welcome to AI Engineer Spotlight, the series where we showcase builders solving real-world problems with AI. In this episode, host Adam sits down with Prachi, the creator of Super People (https://github.com/prachi-b-modi/super-people), an intelligent resume system that transforms the way we track achievements and apply for jobs. Instead of spending hours rewriting resumes for every role, Super People lets you log daily accomplishments — from fine-tuning LLM agents with LangChain and Weaviate to even making pizza — and automatically generates tailored resumes in seconds. By combining vector search with Weaviate semantic matching, Super People ensures only the most relevant experiences surface for each application. If you’re interested in how retrieval-augmented generation (RAG) can power personalized career tools, or just want to see a clever AI project in action, this conversation is packed with insights and a live demo. 👉 Try Super People: https://github.com/prachi-b-modi/super-people 👉 Explore Weaviate: https://weaviate.io Don’t forget to like, comment, and subscribe for more stories from the AI builders community. 00:00 Intro – Welcome to AI Engineer Spotlight 00:16 Meet Prachi, creator of Super People 00:30 The problem with traditional resumes 00:55 Logging daily achievements made simple 02:19 Demo: From AI projects to pizza-making skills 04:11 Generating a tailored resume in seconds 04:34 Why vector databases beat keyword search 06:58 The complete RAG pipeline for careers 07:50 Personalization and subtle skill matching 08:35 Final thoughts on Super People & future of AI resumes 09:08 Closing – Keep building with AI
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Related AI Lessons

I Built GraphRAG From Scratch — Then a December 2025 Paper Made It Look Basic
Learn about HGMem, a new RAG architecture that overcomes limitations of binary graphs, and how it compares to GraphRAG
Medium · RAG
When Should You Use Text2Cypher in a GraphRAG Pipeline
Learn when to use Text2Cypher in a GraphRAG pipeline to retrieve precise graph results from natural language questions
Dev.to AI
How to build a production RAG pipeline in Python (without a vector database)
Learn to build a production-ready RAG pipeline in Python without relying on a vector database, and understand the key considerations for a scalable and efficient implementation
Dev.to · Ayi NEDJIMI
Architecting Sub-150ms Hybrid RAG for Voice Agents: Combining pgvector, BM25, and Async FastAPI…
Learn how to architect a sub-150ms hybrid RAG for voice agents using pgvector, BM25, and Async FastAPI to serve large industrial catalogs
Medium · Python

Chapters (11)

Intro – Welcome to AI Engineer Spotlight
0:16 Meet Prachi, creator of Super People
0:30 The problem with traditional resumes
0:55 Logging daily achievements made simple
2:19 Demo: From AI projects to pizza-making skills
4:11 Generating a tailored resume in seconds
4:34 Why vector databases beat keyword search
6:58 The complete RAG pipeline for careers
7:50 Personalization and subtle skill matching
8:35 Final thoughts on Super People & future of AI resumes
9:08 Closing – Keep building with AI
Up next
Watch this before applying for jobs as a developer.
Tech With Tim
Watch →