0 of 24 complete
Tokens and Tokenization

How model inputs become discrete identifiers and why token boundaries affect cost and meaning.

lab
Embeddings

How learned vectors encode useful similarity and support representation and retrieval.

lesson
Transformer Architecture

How attention feed-forward blocks residual paths and positions transform sequences.

lesson
Training versus Inference

How parameter learning differs from runtime generation and serving operations.

lesson
Context Windows

How finite input and output budgets constrain attention state relevance and cost.

lab
Sampling and Decoding

How logits temperature top-p and deterministic choices shape generated sequences.

lab
Model Families and Lifecycle

How capability modality size versioning deprecation and routing affect model selection.

lesson
Latency and Throughput

How queueing prompt processing generation batching and concurrency determine serving performance.

lab
Message Roles and Instruction Priority

How instruction sources and ordered messages establish conversational control context.

lesson
Prompt Structure

How clear goals constraints context examples and output contracts guide model behavior.

lesson
Structured Outputs

How schemas convert probabilistic text generation into validated application contracts.

lesson
Tool Calling

How models propose typed actions while applications retain execution authority and validation.

lesson
Context Engineering

How systems select assemble order compress and isolate information for each model call.

lesson
State and Memory

How applications persist working state history summaries facts and user-controlled records.

lesson
Exact and Semantic Caching

How reusable computations reduce latency and cost while introducing freshness and correctness risks.

lesson
RAG versus Fine-Tuning

How knowledge access behavior adaptation and tool use solve different system problems.

lab
Ingestion and Chunking

How parsing normalization segmentation metadata and updates create retrievable units.

lab
Vector Search

How embeddings similarity indexes filters and recall tradeoffs retrieve semantic candidates.

lab
Hybrid Search and Reranking

How lexical semantic and learned ranking stages improve candidate precision and recall.

lab
Grounded Generation and Citations

How answer synthesis constrains claims to evidence and preserves inspectable attribution.

lesson
LLM Evaluation

How task definitions datasets metrics rubrics judges and experiments measure system quality.

lab
Grounding and Hallucination

How unsupported claims arise and how evidence constraints and verification reduce them.

lesson
Cost Latency and Reliability

How budgets fallbacks retries routing and service targets balance operating outcomes.

lab
Security and Privacy for LLM Systems

How untrusted inputs sensitive data tools and external knowledge expand the threat model.

lesson

Path outcomes

  • Explain the complete anatomy of an LLM application
  • Select context retrieval tool and adaptation strategies
  • Design measurable secure and economically viable systems