Private Building LLM Apps (RAG & Agents) lessons with AI
Building LLM Apps (RAG & Agents) with a live private lesson: the teacher talks with you out loud and explains on a shared board, moving at your pace through a clear plan, lesson after lesson.
Teacher: Noam
- Course updated 11/2026
- Hebrew, and 5 more languages
- 3 levels: Beginners · Intermediate · Advanced
- 36 lessons · about 20 hours of lessons
Building LLM Apps (RAG & Agents)
Building LLM Apps (RAG & Agents) with a live private lesson: the teacher talks with you out loud and explains on a shared board, moving at your pace through a clear plan, lesson after lesson.
12 lessons · 4 modules · Live private lesson with the teacher on the board
What you'll learn
- The LLM and the First API Call
- Tokens, Context and Cost
- Controlling Output: Prompts and Structured Output
- From Prototype to Responsible App
- Embeddings and Vector Stores
- RAG: From Documents to Answers
- Tool Calling
- Agents and Loops
- Evaluation (Evals)
- Security and Prompt Injection
- Production Monitoring and Operations
Related topics
What's included
- Live 1:1 lessons with an AI tutor on a shared board
- 20 hours of live one-on-one lessons
- 36 lessons on a shared board, each with a clear goal
- Practice and a understanding check in every lesson
- A summary after every lesson, saved in the history
- A completion certificate for each level
- Computer, tablet or phone
- Hebrew, plus 5 more languages
Course plan
3 levels · 11 modules · 36 lessons · 19 hr 30 min total
BeginnersBeginner: From the First API Call to Structured Output4 modules • 12 lessons • 6 hr 25 min
The LLM and the First API Call3 lessons • 1 hr 35 min
- 1What an LLM Actually DoesTrial lessonabout 30 min
- 2Your First API Callabout 35 min
- 3Messages, Roles and Multi-Turn Conversationsabout 30 min
Tokens, Context and Cost3 lessons • 1 hr 35 min
- 4Tokens: The Unit the Model Seesabout 30 min
- 5The Context Window and Conversation Memoryabout 30 min
- 6Cost, Latency and Model Choiceabout 35 min
Controlling Output: Prompts and Structured Output4 lessons • 2 hr 5 min
- 7Sampling: Temperature and Consistencyabout 25 min
- 8Prompt Engineering Basics for Appsabout 35 min
- 9Structured Output: JSON and Schemasabout 35 min
- 10Validation, Errors and Retriesabout 30 min
From Prototype to Responsible App2 lessons • 1 hr 10 min
- 11Keys, Privacy and Responsible Useabout 30 min
- 12Project: End-to-End Customer Ticket Classifierabout 40 min
IntermediateIntermediate: Embeddings, RAG and Tool Calling3 modules • 12 lessons • 6 hr 30 min
Embeddings and Vector Stores3 lessons • 1 hr 30 min
- 1Embeddings: Meaning as a Vectorabout 30 min
- 2Similarity and Semantic Searchabout 30 min
- 3Vector Databases: Indexing, ANN and Metadataabout 30 min
RAG: From Documents to Answers5 lessons • 2 hr 45 min
- 4Document Chunkingabout 35 min
- 5The End-to-End RAG Pipelineabout 35 min
- 6Grounded Answers and Citationsabout 30 min
- 7Better Retrieval: Hybrid, Reranking, Query Rewritingabout 35 min
- 8Diagnosing RAG Failuresabout 30 min
Tool Calling4 lessons • 2 hr 15 min
- 9Tool Calling: The Basic Cycleabout 30 min
- 10Designing Good Toolsabout 30 min
- 11Multiple Tools, Parallel Calls and Errorsabout 35 min
- 12Project: Document Assistant with RAG as a Toolabout 40 min
AdvancedAdvanced: Agents, Evals, Security and Production4 modules • 12 lessons • 6 hr 35 min
Mapped to exam: Design review מסכם: תכנון סוכן לתרחיש אמיתי עם מצבי כשל, eval לכל כשל, הגנות וניטור
Agents and Loops4 lessons • 2 hr 10 min
- 1The Agent Loop: Agent vs Workflowabout 30 min
- 2Workflow Patterns: Chaining, Routing, Parallelizationabout 35 min
- 3Agent State, Memory and Planningabout 35 min
- 4Human-in-the-Loop and Multi-Agent Systemsabout 30 min
Evaluation (Evals)3 lessons • 1 hr 40 min
- 5Evals: Test Sets, Graders and Metricsabout 35 min
- 6LLM-as-Judge: Rubrics and Calibrationabout 30 min
- 7Evaluating RAG and Agentsabout 35 min
Security and Prompt Injection2 lessons • 1 hr 5 min
- 8Threat Model: Direct and Indirect Prompt Injectionabout 30 min
- 9Defense in Depth: Permissions, Guardrails and Outputabout 35 min
Production Monitoring and Operations3 lessons • 1 hr 40 min
- 10Observability: Tracing, Logs and Metricsabout 30 min
- 11Production Reliability: Versioning, Fallbacks and CIabout 30 min
- 12Capstone: Design Review of a Production Agentabout 40 min
What you need
- No prior knowledge needed for beginner level: the teacher checks what you already know and starts from there
- For higher levels: what you learned at the level before (you can skip it if you already know it)
- A computer, tablet or phone with a microphone, and a browser
Who it's for
- Adults: for work, study, an exam, or just curiosity
Exams and certifications
- Advanced: Design review מסכם: תכנון סוכן לתרחיש אמיתי עם מצבי כשל, eval לכל כשל, הגנות וניטור
More courses in this track
Natural Language Processing (NLP)
with Noam
Live 1:1 lesson with an AI teacherabout 20 hours35 lessons3 levelsGenerative AI & Prompt Engineering
with Noa
Live 1:1 lesson with an AI teacherabout 19 hours36 lessons3 levels
Your teacher
NoamAI private tutor, in a live lesson on a shared boardA private AI teacher who teaches in a live conversation: asks, listens, draws on the board, and lets you solve it yourself with hints. Remembers what you've learned and starts each lesson where you left off.
What's a lesson like?
Your child talks with the teacher out loud, like a video call, and asks about anything unclear.
The teacher explains, writes and draws on a shared board, and your child solves along on the same board.
Snap a photo of a worksheet or homework and work through it, one problem at a time.
Parents get a report: study time, what went well and what needs more practice.
Lesson rules
- Just Learning
FAQ
- How does a private Building LLM Apps (RAG & Agents) lesson work?
- Pick Building LLM Apps (RAG & Agents) and a level, then talk with the teacher out loud. The teacher asks what you already know, explains, writes and draws on the board, and lets you solve on your own with hints until it's clear.
- How long does the Building LLM Apps (RAG & Agents) course take?
- 12 lessons of about 32 minutes at the first level, at your own pace. You can pause, go back, or skip what you already know.
- Do I need prior knowledge?
- Not for beginner level. At the start of the first lesson the teacher checks what you already know and adjusts the level, and you can jump straight to an advanced level.
- How do I start for free?
- Sign in with Google or a code sent to your email, enter your child's name and grade, and the lesson starts right away. Every family gets 45 free lesson minutes in any subject, counted by actual lesson time, with no credit card. Then choose a paid plan and cancel anytime.
- What device do I need?
- Any computer, tablet or phone with a browser and a microphone. You can also install the site as an app on your home screen.
Want to try it?
Sign in, enter your child's name and grade, and the lesson begins. 45 free lesson minutes, no credit card.
Start for freeShiur Prati with AI: what it is and how it works







