$\newline Logo$

Go to Preview Lesson

Go to Preview Lesson

LESSON 2.2From Theory to Practice — Building Your First LLM Application

LESSON 2.3Intro to AI-Centric Evaluation

MODULE 1
Onboarding & Tooling
MODULE 2
AI Projects and Use Cases
MODULE 3
Prompt Engineering & Embeddings
- LESSON 3.1Prompt Engineering — From Structure to Evaluation (Mini Project 1)
- LESSON 3.2Tokens, Embeddings & Modalities — Foundations of Understanding Text, Image, and Audio
MODULE 4
Multimodal + Retrieval-Augmented Systems
- LESSON 4.1Multimodal Embeddings (CLIP)
- LESSON 4.2RAG & Retrieval Techniques (Mini Project 2)
MODULE 5
Classical Language Models
- LESSON 5.1N-Gram Language Models (Mini Project 3)
- LESSON 5.2Triplet Loss Embedding Finetuning for Search & Ranking (Mini Project 4)
MODULE 6
Attention & Finetuning
- LESSON 6.1Building Self-Attention Layers
- LESSON 6.2Instructional Finetuning with LoRA (Mini Project 5)
MODULE 7
Architectures & Multimodal Systems
- LESSON 7.1Feedforward Networks & Loss-Centric Training
- LESSON 7.2Multimodal Finetuning (Mini Project 6)
MODULE 8
Assembling & Training Transformers
- LESSON 8.1Full Transformer Architecture (From Scratch)
- LESSON 8.2Advanced RAG & Retrieval Methods
MODULE 9
Specialized Finetuning Projects
- LESSON 9.1CLIP Fine-Tuning for Insurance
- LESSON 9.2Math Reasoning & Tool-Augmented Finetuning
MODULE 10
Advanced RLHF & Engineering Architectures
- LESSON 10.1Preference-Based Finetuning — DPO, PPO, RLHF & GRPO
- LESSON 10.2Building AI Code Agents — Case Studies from Copilot, Cursor, Windsurf
MODULE 11
Agents & Multimodal Code Systems
- LESSON 11.1Agent Design Patterns
- LESSON 11.2Text-to-SQL and Text-to-Music Architectures
MODULE 12
Deep Internals & Production Pipelines
- LESSON 12.1Positional Encoding + DeepSeek Internals
- LESSON 12.2LLM Production Chain (Inference, Deployment, CI/CD)
MODULE 13
Enterprise LLMs, Hallucinations & Career Growth
MODULE 14
AI Accelerator
- LESSON 14.1AI Accelerator
MODULE 15
Career Prep
- LESSON 15.1Career Prep

Go to Next Lesson

Go to Next Lesson

LESSON 3.1Prompt Engineering — From Structure to Evaluation (Mini Project 1)

Go Pro
Log In

Intro to AI-Centric Evaluation

- Metrics and Evaluation Design - Foundation for Future Metrics Work - Building synthetic data for AI applications

Courses
AI Accelerator
Intro to AI-Centric Evaluation

Go To Previous Lesson
From Theory to Practice — Building Your First LLM Application
- Understand how inference works in LLMs (prompt processing vs. autoregressive decoding) - Explore real-world AI applications: RAG, vertical models, agents, multimodal tools - Learn the five phases of the model lifecycle: pretraining to RLHF to evaluation - Compare architecture types: generic LLMs vs. ChatGPT vs. domain-specialized models - Work with tools like Hugging Face, Modal, and vector databases - Build a “Hello World” LLM inference API using OPT-125m on Modal
Go To Next Lesson
Prompt Engineering — From Structure to Evaluation (Mini Project 1)
- Learn foundational prompt styles: vague vs. specific, structured formatting, XML-tagging - Practice prompt design for controlled output: enforcing strict JSON formats with Pydantic - Discover failure modes and label incorrect LLM behavior (e.g., hallucinations, format issues) - Build early evaluators to measure LLM output quality and rule-following - Write your first "LLM-as-a-judge" prompts to automate pass/fail decisions - Iterate prompts based on analysis-feedback loops and evaluator results - Explore advanced prompting techniques: multi-turn, rubric-based human alignment, and A/B testing - Experiment with `dspy` for signature-based structured prompting and validation