🤖 AI & IT Training
Build AI That Answers from Your Own Data — Intro to RAG
⏱ Training hours4 hours
🏢 FormatOn-site delivery · Customized design
👤 InstructorJohn Kim
✅ Key outcomeBuild an AI answer system grounded in your company documents
A focused 4-hour hands-on course in which you build a custom AI system connected to your company’s work data using RAG (Retrieval-Augmented Generation). Led by John Kim, CEO of Nanum Consulting, you go step by step from core RAG concepts to designing an architecture that connects company documents, then build a working system with Supabase and Voyage AI. Alongside the theory, you build a RAG system you can use in your own workplace, so you leave able to develop AI solutions tailored to your company’s data. Going beyond general ChatGPT use, you create a custom AI grounded in your organization’s specialized knowledge and data, which can significantly improve work efficiency and decision accuracy. The curriculum is proven in Nanum Consulting’s training for 50+ major corporations and institutions.
💻 Start learning this topic with an online course →Who is this course for?
This course suits practitioners and leaders at companies and institutions that want to build AI and IT skills. It is especially recommended for organizations aiming to understand RAG and build AI connected to their business data.
What will you learn?
- Gain the ability to understand RAG technology and build AI connected to your work data
Curriculum
Module 1: Understanding RAG and why it matters
- The generative AI hallucination problem – analyzing why ungrounded answers are generated, with case studies
- Defining RAG (Retrieval-Augmented Generation) – understanding how document retrieval and generation are combined
- Comparing conventional AI and RAG – analyzing differences in accuracy, reliability, and enterprise usability
- The business value of adopting RAG – protecting confidential company data, using up-to-date information, and cost efficiency
- How RAG resolves hallucinations – analyzing the process of generating answers grounded in real data
- The full RAG architecture flow – understanding each stage: embedding, vector store, retrieval, and generation
Module 2: RAG system architecture for company documents
- Supabase vector database structure – how document storage, vectorization, and search work
- The role of the Voyage AI embedding model – hands-on practice converting text into high-dimensional vectors
- Document preprocessing and chunking strategy – methods for splitting long documents into optimal sizes
- How semantic search works – finding documents by meaning, not keywords
- Vector similarity calculation and ranking – understanding the criteria for judging the relevance of retrieved documents
- Connecting to Claude – feeding search results into the prompt to generate the final answer
Module 3: Hands-on with Supabase and Voyage AI
- Creating a Supabase project and setting up vector tables – building a database in a real cloud environment
- Connecting the Voyage AI API and generating embeddings – converting sample documents into vectors and storing them
- Using no-code tools (Make, Zapier) – an automated workflow from document upload to vectorization
- A RAG application prototype built with Claude Code – a working chat interface
- Evaluating search result quality and tuning parameters – adjusting Top-K values and similarity thresholds
- Testing and deploying your RAG system – verifying it works with a variety of questions and sharing it
Module 4: Hands-on with Supabase and Voyage AI
- Creating a Supabase project and setting up vector tables – building a database in a real cloud environment
- Connecting the Voyage AI API and generating embeddings – converting sample documents into vectors and storing them
- Using no-code tools (Make, Zapier) – an automated workflow from document upload to vectorization
- A RAG application prototype built with Claude Code – a working chat interface
- Evaluating search result quality and tuning parameters – adjusting Top-K values and similarity thresholds
- Testing and deploying your RAG system – verifying it works with a variety of questions and sharing it
Tools used in this course
Expected results / After the course
- Build an AI answer system grounded in your company documents
On-site training references
Korea Expressway CorporationNanum ConsultingBioProtechKMAas instructorBracco Imaging Koreaand more
About the instructor
John KimInstructor John Kim, author of “B2B Marketing Design” and CEO of Nanum ConsultingView profile →
Related courses
Recommended online courses
Start with an Online Course
Before you book on-site training, preview the essentials of this topic in an online course.
AI · Online Courses
Claude Cowork · Hands-On Basics
An introductory hands-on course for building work tools that run on plain conversational instructions.
KRW 59,000 (≈ US$44)89,000View Course →
AI · Online Courses
Practical AI for Corporate Instructors
Use AI in your daily work, from lesson prep to content creation.
KRW 59,000 (≈ US$44)89,000View Course →
We tailor this course to your company
From diagnosis to execution — Nanum Consulting
FAQ
Well suited to developers, data analysts, and planners who want to bring AI into their work. Especially recommended for practitioners interested in building AI systems that use internal company documents or knowledge bases.
The core is not theory but hands-on practice building a real RAG system with Supabase and Voyage AI. It is a practical curriculum that takes you from the system architecture for connecting your own company documents to a working implementation, all within 4 hours.
Yes. John Kim's structured curriculum moves step by step, from understanding RAG concepts to hands-on work with Supabase and Voyage AI. By the end, you can build a RAG system ready to apply to your company work right away.
John Kim is an expert who has delivered AI and data training at many companies. His practical, hands-on training on building RAG systems, which combines theory with real-world work, earns high satisfaction.
Build AI That Answers from Your Own Data — Intro to RAG
A focused 4-hour hands-on course in which you build a custom AI system connected to your company’s work data using RAG (Retrieval-Augmented Generation)
Training objectives
- Gain the ability to understand RAG technology and build AI connected to your work data
Expected results
- Build an AI answer system grounded in your company documents
Curriculum
Module 1Module 1: Understanding RAG and why it matters
- The generative AI hallucination problem – analyzing why ungrounded answers are generated, with case studies
- Defining RAG (Retrieval-Augmented Generation) – understanding how document retrieval and generation are combined
- Comparing conventional AI and RAG – analyzing differences in accuracy, reliability, and enterprise usability
- The business value of adopting RAG – protecting confidential company data, using up-to-date information, and cost efficiency
- How RAG resolves hallucinations – analyzing the process of generating answers grounded in real data
- The full RAG architecture flow – understanding each stage: embedding, vector store, retrieval, and generation
Module 2Module 2: RAG system architecture for company documents
- Supabase vector database structure – how document storage, vectorization, and search work
- The role of the Voyage AI embedding model – hands-on practice converting text into high-dimensional vectors
- Document preprocessing and chunking strategy – methods for splitting long documents into optimal sizes
- How semantic search works – finding documents by meaning, not keywords
- Vector similarity calculation and ranking – understanding the criteria for judging the relevance of retrieved documents
- Connecting to Claude – feeding search results into the prompt to generate the final answer
Module 3Module 3: Hands-on with Supabase and Voyage AI
- Creating a Supabase project and setting up vector tables – building a database in a real cloud environment
- Connecting the Voyage AI API and generating embeddings – converting sample documents into vectors and storing them
- Using no-code tools (Make, Zapier) – an automated workflow from document upload to vectorization
- A RAG application prototype built with Claude Code – a working chat interface
- Evaluating search result quality and tuning parameters – adjusting Top-K values and similarity thresholds
- Testing and deploying your RAG system – verifying it works with a variety of questions and sharing it
Module 4Module 4: Hands-on with Supabase and Voyage AI
- Creating a Supabase project and setting up vector tables – building a database in a real cloud environment
- Connecting the Voyage AI API and generating embeddings – converting sample documents into vectors and storing them
- Using no-code tools (Make, Zapier) – an automated workflow from document upload to vectorization
- A RAG application prototype built with Claude Code – a working chat interface
- Evaluating search result quality and tuning parameters – adjusting Top-K values and similarity thresholds
- Testing and deploying your RAG system – verifying it works with a variety of questions and sharing it
About the instructor
John Kim, Lead Instructor
10 years in industry · 15 years teaching (3,000+ lectures)
Education
· MBA (advanced major: Marketing), Korea University Graduate School of Business (graduated)
· Sungkyunkwan University Consultant Program (completed)
· Sogang University Graduate School of Business, Short-Term MBA (completed)
· Seoul National University Lifelong Education Instructor Development Program (completed)
· Chung-Ang University, B.A. in English Language and Literature (graduated)
Experience
· Current: CEO, Nanum Consulting
· Formerly at Hyosung Corp., Daeduck Electronics and Shinhan Diamond: overseas assignments and strategic planning (10+ years)
· Current partner instructor, Expert Consulting
· Current: Partner instructor, PSI Consulting
· (Current) Partner instructor, Korea SMEs and Startups Agency and SME Training Institute
Credentials and publications
· Certified consultant
· Certified teacher
· Completed official IDEO Design Thinking training
· B2B Marketing Design (1 Apr 2025)
· The Chinese Diamond Tool Market: Present and Future (co-authored, Korea Tool Association)
· Battles That Changed History and Innovative Weapons (in progress)