Appendix P: Keyword Index
An automatically generated index of key terms and their chapter locations.
**:
-** — Audio & Speech, Video & Multimodal
: 1. — Prompt Engineering, Security
A
A1. — First LLM App, Agentic Systems, Responsible AI, Mentorship, Cost Engineering
A2. — First LLM App, Agentic Systems, Responsible AI, Mentorship, Cost Engineering
A3. — First LLM App, Agentic Systems, Responsible AI, Mentorship, Cost Engineering
A4. — First LLM App, Agentic Systems, Responsible AI, Mentorship, Cost Engineering
Accuracy — ML Fundamentals, Audio & Speech
agent — AI Engineering Landscape, First LLM App, LLM/NLP Foundations, Prompt Engineering, RAG Systems (+12 more)
Agents — Cloud AI Providers, Multi-Cloud Patterns
AgentState — Orchestration Frameworks, Observability & Guardrails
AI Incident Database — Responsible AI, Project Ownership
Analysis — Orchestration Frameworks, Observability & Guardrails, Performance
Architecture — LLM Deployment, Audio & Speech, Data Architecture
Architecture Decision Records — Technical Communication, System Design, Decision Making
Ask clarifying questions — Technical Communication, Mentorship
attention — AI Engineering Landscape, ML Fundamentals, LLM/NLP Foundations, Prompt Engineering, RAG Systems (+21 more)
B
batching — AI Engineering Landscape, ML Fundamentals, First LLM App, LLM/NLP Foundations, Prompt Engineering (+8 more)
Batching — LLM Deployment, System Design
Batching effects — ML Fundamentals, Backend Engineering
Best For — Cloud AI Providers, Multi-Cloud Patterns
Best Models — Cloud AI Providers, Multi-Cloud Patterns
Boundaries — Security, Mentorship
Brown et al. (2020), “Language Models are Few-Shot Learners” — AI Engineering Landscape, ML Fundamentals
Build vs. Buy Decision Framework — Decision Making, Cost Engineering
C
Caching — First LLM App, Data Architecture, Cost Engineering
Case Studies — Cloud AI Providers, Research to Production, Reliability
chain-of-thought — First LLM App, LLM/NLP Foundations, Prompt Engineering, Agentic Systems, MLOps & Evaluation (+1 more)
Challenge — Prompt Engineering, Performance
Chapter 10 (Orchestration & Agent Frameworks) — AI Engineering Landscape, Agentic Systems, Observability & Guardrails
Chapter 12 (Cloud AI Deployment) — Orchestration Frameworks, Observability & Guardrails, Reliability
Chapter 14 (Backend Engineering for AI) — Python for AI, First LLM App
Chapter 15 (Evaluation) — First LLM App, Prompt Engineering
Chapter 15 (MLOps & Evaluation) — ML Fundamentals, First LLM App, RAG Systems, Observability & Guardrails, Video & Multimodal (+4 more)
Chapter 15 (MLOps) — Vision & Document AI, Responsible AI
Chapter 16 (Security & Adversarial Robustness) — Agentic Systems, Observability & Guardrails, Multi-Cloud Patterns
Chapter 16 (Security) — First LLM App, Responsible AI
Chapter 17 (Vision & Document AI) — Audio & Speech, Video & Multimodal
Chapter 21 (Deepening Technical Expertise) — Project Ownership, Mentorship, Research to Production
Chapter 22 (Project Ownership & Delivery) — Technical Expertise, Technical Communication, Cross-Team Leadership
Chapter 23 (Technical Communication) — Technical Expertise, Project Ownership, Mentorship, Decision Making, Research to Production (+1 more)
Chapter 23 (Technical Decision Making) — Technical Expertise, Project Ownership, Technical Communication, Research to Production
Chapter 24 (Mentorship Foundations) — Technical Expertise, Project Ownership, Technical Communication, Cross-Team Leadership
Chapter 25 (System Design at Scale) — Project Ownership, Decision Making, Performance, Cross-Team Leadership, Data Architecture (+1 more)
Chapter 26 (Cross-Team Technical Leadership) — Technical Communication, Mentorship, Decision Making
Chapter 27 (Performance Engineering) — ML Fundamentals, LLM Deployment, System Design, Research to Production, Cost Engineering
Chapter 30 (Data Architecture for AI) — RAG Systems, MLOps & Evaluation
Chapter 31 (Reliability Engineering) — Python for AI, Agentic Systems, Cloud AI Providers, Multi-Cloud Patterns, System Design (+2 more)
Chapter 32 (Cost Engineering) — LLM Deployment, Cloud AI Providers, Multi-Cloud Patterns, System Design, Decision Making (+3 more)
Chapter 4 (Your First LLM Application) — AI Engineering Landscape, Python for AI
Chapter 5 (LLM Foundations) — ML Fundamentals, Prompt Engineering, LLM Deployment, Vision & Document AI
Chapter 5 (LLM/NLP Foundations) — AI Engineering Landscape, ML Fundamentals, RAG Systems
Chapter 5: LLM/NLP Foundations — Prompt Engineering, LLM Deployment
Chapter 6 (Prompt Engineering) — First LLM App, LLM/NLP Foundations, RAG Systems, Agentic Systems, LLM Deployment
Chapter 7 (RAG Systems) — ML Fundamentals, First LLM App, LLM/NLP Foundations, Prompt Engineering, Agentic Systems (+9 more)
Chapter 8 (Agentic Systems) — First LLM App, LLM/NLP Foundations, Prompt Engineering, RAG Systems, LLM Deployment (+3 more)
Chapter 9 (Deployment) — First LLM App, LLM/NLP Foundations, Vision & Document AI
Chapter 9 (LLM Deployment & Infrastructure) — Python for AI, Cloud AI Providers, Multi-Cloud Patterns, System Design, Performance (+4 more)
Check Your Answers — First LLM App, Agentic Systems, Responsible AI, Mentorship, Cost Engineering
chunking — AI Engineering Landscape, Python for AI, First LLM App, RAG Systems, Agentic Systems (+8 more)
CircuitBreaker — System Design, Reliability
Cold storage — Backend Engineering, MLOps & Evaluation
Common Failure Patterns — Agentic Systems, Research to Production
Common Pitfalls and How to Avoid Them — Performance, Cross-Team Leadership, Data Architecture
Communicating Uncertainty — Project Ownership, Technical Communication
Complete code — First LLM App, Video & Multimodal
Compliance — Cloud AI Providers, Multi-Cloud Patterns, Data Architecture
Compositionality — Vision & Document AI, Video & Multimodal
Conceptual Questions — AI Engineering Landscape, Python for AI, ML Fundamentals, First LLM App, LLM/NLP Foundations (+27 more)
Connections to Other Chapters — AI Engineering Landscape, Python for AI, ML Fundamentals, First LLM App, LLM/NLP Foundations (+27 more)
Cons — Vision & Document AI, System Design
Consistency — LLM/NLP Foundations, MLOps & Evaluation, System Design
Context — First LLM App, Prompt Engineering, Backend Engineering, Audio & Speech, Mentorship (+2 more)
context window — AI Engineering Landscape, LLM/NLP Foundations, Prompt Engineering, RAG Systems, Agentic Systems (+5 more)
Continuous batching — LLM/NLP Foundations, LLM Deployment, System Design, Performance, Cost Engineering
Contrastive learning — ML Fundamentals, RAG Systems
Control — Orchestration Frameworks, Cloud AI Providers
Correctness — MLOps & Evaluation, Technical Communication
Cosine similarity — First LLM App, RAG Systems
Cost — AI Engineering Landscape, First LLM App, Cloud AI Providers, MLOps & Evaluation, Audio & Speech
Cost Optimization Strategies — Data Architecture, Cost Engineering
Cost Tracking — First LLM App, Observability & Guardrails
Course correction — Agentic Systems, Mentorship
Critical — Security, Responsible AI
Customization — AI Engineering Landscape, Cloud AI Providers
D
Dao et al. (2022), “FlashAttention” — Performance, Research to Production
Data Engineers — AI Engineering Landscape, Project Ownership
Data leakage — ML Fundamentals, Data Architecture
Data privacy — AI Engineering Landscape, Decision Making
Decision framework — Prompt Engineering, RAG Systems
Decision Framework — LLM Deployment, Observability & Guardrails
Decision Frameworks — Backend Engineering, MLOps & Evaluation
Decision records — Technical Expertise, Mentorship
Deep Dives — AI Engineering Landscape, ML Fundamentals, First LLM App, LLM/NLP Foundations, Prompt Engineering (+22 more)
Deep Dives (For Specialists) — LLM Deployment, Responsible AI
Define criteria — ML Fundamentals, Decision Making
Deployment — First LLM App, Cloud AI Providers
Design Exercises — AI Engineering Landscape, LLM/NLP Foundations, Prompt Engineering, RAG Systems, Agentic Systems (+20 more)
Detailed Design — Technical Communication, Decision Making
Directness — Technical Communication, Mentorship
Documented — MLOps & Evaluation, Project Ownership
Drawbacks — Technical Communication, Decision Making
E
Efficiency — First LLM App, LLM/NLP Foundations, MLOps & Evaluation
embedding — AI Engineering Landscape, Python for AI, ML Fundamentals, First LLM App, LLM/NLP Foundations (+24 more)
Embeddings — ML Fundamentals, LLM/NLP Foundations
Enterprise Features — Orchestration Frameworks, Cloud AI Providers
Error handling — Orchestration Frameworks, Technical Communication
Error recovery — Agentic Systems, Video & Multimodal
Essential — AI Engineering Landscape, ML Fundamentals, First LLM App, LLM/NLP Foundations, Prompt Engineering (+22 more)
Essential (Read These) — LLM Deployment, Responsible AI
Evaluation — ML Fundamentals, RAG Systems
Evaluation and Quality Assurance — Vision & Document AI, Video & Multimodal
Example — Security, Responsible AI
Example calculation — LLM Deployment, Reliability
Exercise 1. [Senior] — AI Engineering Landscape, LLM/NLP Foundations, Prompt Engineering, RAG Systems, Agentic Systems (+13 more)
Exercise 1. [Staff] — System Design, Decision Making, Performance, Reliability, Cost Engineering
Exercise 2. [Staff] — AI Engineering Landscape, LLM/NLP Foundations, Prompt Engineering, RAG Systems, Agentic Systems (+18 more)
Exercise 3: Build vs. Buy Analysis — Decision Making, Cost Engineering
Exercise 4: Incident Response Simulation — Responsible AI, Reliability
F
Failure analysis — First LLM App, RAG Systems, Agentic Systems
Feedback loops — Data Architecture, Reliability
few-shot — AI Engineering Landscape, ML Fundamentals, First LLM App, LLM/NLP Foundations, Prompt Engineering (+5 more)
fine-tuning — AI Engineering Landscape, ML Fundamentals, LLM/NLP Foundations, Prompt Engineering, RAG Systems (+12 more)
Fine-tuning — Cloud AI Providers, Multi-Cloud Patterns
Fix — Prompt Engineering, RAG Systems, Agentic Systems, LLM Deployment, Security (+2 more)
Fix: — LLM/NLP Foundations, Prompt Engineering, Orchestration Frameworks, Observability & Guardrails, Cloud AI Providers (+13 more)
Flash Attention — LLM/NLP Foundations, Performance
Follow up — Technical Communication, Mentorship
Full implementation — Prompt Engineering, RAG Systems, Agentic Systems, LLM Deployment, Backend Engineering (+5 more)
function calling — AI Engineering Landscape, Prompt Engineering, Agentic Systems, Observability & Guardrails, Cloud AI Providers (+1 more)
Further Reading — AI Engineering Landscape, Python for AI, ML Fundamentals, First LLM App, LLM/NLP Foundations (+24 more)
G
Generates — RAG Systems, Performance
Graceful degradation — Agentic Systems, LLM Deployment
Graceful Degradation — Backend Engineering, Reliability
Grouped-Query Attention (GQA) — LLM/NLP Foundations, Performance
Growth Areas: — Project Ownership, Research to Production
guardrails — AI Engineering Landscape, ML Fundamentals, Prompt Engineering, Agentic Systems, Orchestration Frameworks (+5 more)
H
hallucination — AI Engineering Landscape, ML Fundamentals, First LLM App, Prompt Engineering, RAG Systems (+7 more)
Handling Disagreements — Project Ownership, Research to Production
Haystack — AI Engineering Landscape, Orchestration Frameworks
High — Security, Responsible AI
Historical Context — LLM Deployment, Orchestration Frameworks
HNSW (Hierarchical Navigable Small World) — First LLM App, RAG Systems
Hot storage — Backend Engineering, MLOps & Evaluation
How they fixed it — Prompt Engineering, RAG Systems, Reliability
Human evaluation — ML Fundamentals, MLOps & Evaluation
Human-in-the-loop — Prompt Engineering, Security
Hybrid approach — Agentic Systems, Decision Making
Hybrid search — AI Engineering Landscape, First LLM App, RAG Systems
I
Impact — Mentorship, System Design
Implement caching — First LLM App, Cloud AI Providers
inference — AI Engineering Landscape, Python for AI, ML Fundamentals, LLM/NLP Foundations, Prompt Engineering (+20 more)
Integration Patterns — Observability & Guardrails, Backend Engineering
Interpretability — ML Fundamentals, Agentic Systems
Interview Preparation — AI Engineering Landscape, Mentorship
Introduction — AI Engineering Landscape, Python for AI, ML Fundamentals, First LLM App, LLM/NLP Foundations (+26 more)
K
Kahneman (2011), “Thinking, Fast and Slow” — Technical Expertise, Project Ownership
Keshav (2007), “How to Read a Paper” — Technical Expertise, Research to Production
Key differences — Prompt Engineering, RAG Systems, Agentic Systems, LLM Deployment, Security (+2 more)
Key insight — Prompt Engineering, LLM Deployment, System Design, Reliability
Key insights — Mentorship, Performance
Key Principles — Orchestration Frameworks, Observability & Guardrails
Key Takeaways — First LLM App, LLM/NLP Foundations, Prompt Engineering, RAG Systems, Agentic Systems (+17 more)
Kleppmann (2017), “Designing Data-Intensive Applications” — Backend Engineering, Data Architecture
KV cache — AI Engineering Landscape, LLM/NLP Foundations, LLM Deployment, Responsible AI, Technical Expertise (+3 more)
KV caching — LLM/NLP Foundations, LLM Deployment, System Design
Kwon et al. (2023), “PagedAttention” — Backend Engineering, System Design
Kwon et al. (2023), “PagedAttention/vLLM” — Research to Production, Cost Engineering
L
LangChain — AI Engineering Landscape, Orchestration Frameworks
Langfuse — AI Engineering Landscape, Observability & Guardrails
LangSmith — AI Engineering Landscape, Observability & Guardrails
Latency — AI Engineering Landscape, Cloud AI Providers, Audio & Speech
latency — AI Engineering Landscape, Python for AI, First LLM App, LLM/NLP Foundations, Prompt Engineering (+25 more)
Legal and Compliance — AI Engineering Landscape, Project Ownership
LlamaIndex — AI Engineering Landscape, Orchestration Frameworks
LLM — AI Engineering Landscape, Python for AI, ML Fundamentals, First LLM App, LLM/NLP Foundations (+26 more)
LLM Provider Comparison — Cloud AI Providers, Cost Engineering
Low — Security, Responsible AI
M
Maintainability — MLOps & Evaluation, Research to Production
Market Position — Orchestration Frameworks, Observability & Guardrails
Medium — Security, Responsible AI
Memory bandwidth is the bottleneck — LLM Deployment, Performance
memory-bandwidth bound — LLM Deployment, System Design
Migration Strategies — Orchestration Frameworks, Data Architecture
Mitigation strategies — Prompt Engineering, RAG Systems, System Design, Decision Making
Model size — System Design, Cost Engineering
Model updates — ML Fundamentals, Backend Engineering
Motivation — Technical Communication, Decision Making
Multi-Query Attention (MQA) — LLM/NLP Foundations, Performance
Multilingual — RAG Systems, Audio & Speech
N
NIST AI Risk Management Framework — Security, Responsible AI
Non-determinism — AI Engineering Landscape, MLOps & Evaluation
O
Observability — Orchestration Frameworks, Observability & Guardrails
OpenAI — AI Engineering Landscape, First LLM App
Outcome — Mentorship, Decision Making
P
PagedAttention — LLM Deployment, System Design, Performance
Patterson et al., “Crucial Conversations” — Technical Communication, Cross-Team Leadership
Performance — Orchestration Frameworks, Observability & Guardrails, Technical Communication
Philosophy — Orchestration Frameworks, Observability & Guardrails
Practical Exercises — AI Engineering Landscape, Python for AI, ML Fundamentals, First LLM App, LLM/NLP Foundations (+27 more)
Practical implications — ML Fundamentals, System Design
Practical Resources — Backend Engineering, Vision & Document AI, Responsible AI, Project Ownership, Technical Communication (+2 more)
Prerequisites — First LLM App, LLM/NLP Foundations, Prompt Engineering, RAG Systems, Agentic Systems (+20 more)
Prevention — Responsible AI, Project Ownership
Principle of least privilege — Agentic Systems, Security
Problem 1. [IC2] — AI Engineering Landscape, LLM/NLP Foundations, Prompt Engineering, RAG Systems, Agentic Systems (+16 more)
Problem 1. [Senior] — System Design, Decision Making, Performance, Reliability, Cost Engineering
Problem 2. [Senior] — AI Engineering Landscape, LLM/NLP Foundations, Prompt Engineering, RAG Systems, Agentic Systems (+16 more)
Problem 2. [Staff] — System Design, Decision Making, Performance, Reliability, Cost Engineering
Problem 3. [Staff] — AI Engineering Landscape, LLM/NLP Foundations, Prompt Engineering, RAG Systems, Agentic Systems (+21 more)
Product Managers — AI Engineering Landscape, Project Ownership
Production Architecture Patterns — Vision & Document AI, Video & Multimodal
Production Considerations — RAG Systems, Agentic Systems, Vision & Document AI
prompt — AI Engineering Landscape, Python for AI, ML Fundamentals, First LLM App, LLM/NLP Foundations (+25 more)
prompt injection — AI Engineering Landscape, First LLM App, Prompt Engineering, Agentic Systems, Observability & Guardrails (+6 more)
Prompt optimization — First LLM App, Cost Engineering
Pros — Vision & Document AI, System Design
Q
Q1. — First LLM App, Agentic Systems, Responsible AI, Mentorship, Cost Engineering
Q1. [IC1] — ML Fundamentals, First LLM App
Q1. [IC2] — AI Engineering Landscape, Python for AI, LLM/NLP Foundations, Prompt Engineering, RAG Systems (+17 more)
Q1. [Senior] — System Design, Decision Making, Performance, Reliability, Cost Engineering
Q2. — First LLM App, Agentic Systems, Responsible AI, Mentorship, Cost Engineering
Q2. [IC1] — ML Fundamentals, First LLM App
Q2. [IC2] — AI Engineering Landscape, Python for AI, LLM/NLP Foundations, Prompt Engineering, RAG Systems (+17 more)
Q2. [Senior] — System Design, Decision Making, Performance, Reliability, Cost Engineering
Q3. — First LLM App, Agentic Systems, Responsible AI, Mentorship, Cost Engineering
Q3. [IC2] — ML Fundamentals, First LLM App
Q3. [Senior] — AI Engineering Landscape, Python for AI, LLM/NLP Foundations, Prompt Engineering, RAG Systems (+17 more)
Q3. [Staff] — System Design, Decision Making, Performance, Reliability, Cost Engineering
Q4. — First LLM App, Agentic Systems, Responsible AI, Mentorship, Cost Engineering
Q4. [IC2] — ML Fundamentals, First LLM App
Q4. [Senior] — AI Engineering Landscape, Python for AI, LLM/NLP Foundations, Prompt Engineering, RAG Systems (+17 more)
Q4. [Staff] — System Design, Decision Making, Performance, Reliability, Cost Engineering
Q5. [Senior] — ML Fundamentals, First LLM App
Q5. [Staff] — AI Engineering Landscape, LLM/NLP Foundations, Prompt Engineering, RAG Systems, Agentic Systems (+21 more)
Quality Indicators: — Technical Expertise, Project Ownership, Research to Production, Data Architecture
quantization — AI Engineering Landscape, ML Fundamentals, LLM/NLP Foundations, RAG Systems, LLM Deployment (+8 more)
Quantization — LLM Deployment, System Design, Performance, Cost Engineering
Questions to ask — Orchestration Frameworks, Responsible AI
Quick Self-Test (10 minutes) — First LLM App, Agentic Systems, Responsible AI, Mentorship, Cost Engineering
R
Radford et al. (2021), “CLIP” — Vision & Document AI, Video & Multimodal
RAG — AI Engineering Landscape, Python for AI, ML Fundamentals, First LLM App, LLM/NLP Foundations (+27 more)
RAG Support — Cloud AI Providers, Multi-Cloud Patterns
Read carefully if — Python for AI, ML Fundamentals
Read-only filesystem — Agentic Systems, Security
Real-World Case Studies — Security, Mentorship
Recommendation — Vision & Document AI, Technical Communication
Recommended Reading — LLM Deployment, Responsible AI
Reliability — AI Engineering Landscape, Observability & Guardrails, Research to Production
Reproducibility — LLM/NLP Foundations, Data Architecture
Requirements — Observability & Guardrails, Cost Engineering
Reranking — AI Engineering Landscape, First LLM App, RAG Systems
reranking — AI Engineering Landscape, ML Fundamentals, First LLM App, LLM/NLP Foundations, RAG Systems (+4 more)
Results — Prompt Engineering, Vision & Document AI, Audio & Speech
Risk Assessment Matrix — Security, Project Ownership
RLHF — ML Fundamentals, LLM/NLP Foundations, MLOps & Evaluation, Technical Expertise, Research to Production
Root cause — Prompt Engineering, RAG Systems, Reliability
S
Safety — Agentic Systems, MLOps & Evaluation
Scale — AI Engineering Landscape, LLM/NLP Foundations, Security
Scenario — RAG Systems, Cost Engineering
Sculley et al. (2015), “Hidden Technical Debt in ML Systems” — Project Ownership, Research to Production, Data Architecture, Reliability
See Also — Prompt Engineering, LLM Deployment
Self-Assessment Checkpoint — AI Engineering Landscape, Python for AI, ML Fundamentals, First LLM App, LLM/NLP Foundations (+27 more)
Self-Assessment Questions: — Technical Expertise, Project Ownership, Research to Production, Data Architecture
SemanticCache — System Design, Cost Engineering
Situation — Mentorship, Decision Making, Performance
Skills Checklist — First LLM App, Agentic Systems, Responsible AI, Mentorship, Cost Engineering
Skim instead if — Python for AI, ML Fundamentals
Skip This Chapter If… — Python for AI, ML Fundamentals
Speculative decoding — LLM Deployment, Performance, Cost Engineering
Speed — LLM Deployment, MLOps & Evaluation
Spot the Problem — AI Engineering Landscape, LLM/NLP Foundations, Prompt Engineering, RAG Systems, Agentic Systems (+24 more)
Staff Engineer Perspective — LLM/NLP Foundations, Prompt Engineering, RAG Systems, Agentic Systems, LLM Deployment (+18 more)
Stage 1: Novice — Technical Expertise, Mentorship
Stage 2: Advanced Beginner — Technical Expertise, Mentorship
Stage 3: Competent — Technical Expertise, Mentorship
Stage 4: Proficient — Technical Expertise, Mentorship
Stage 5: Expert — Technical Expertise, Mentorship
Start simple — Agentic Systems, Orchestration Frameworks
State Management — Agentic Systems, Orchestration Frameworks
streaming — AI Engineering Landscape, Python for AI, First LLM App, Prompt Engineering, Agentic Systems (+14 more)
Summary — AI Engineering Landscape, Python for AI, ML Fundamentals, First LLM App, LLM/NLP Foundations (+27 more)
T
Task — Orchestration Frameworks, Observability & Guardrails, MLOps & Evaluation
temperature — Python for AI, ML Fundamentals, First LLM App, LLM/NLP Foundations, Prompt Engineering (+13 more)
Tensor Parallelism — System Design, Performance
The Contenders — Orchestration Frameworks, Observability & Guardrails
The Curse of Knowledge — Technical Communication, Mentorship
The fix — Performance, Data Architecture
The Lost-in-the-Middle Problem — Prompt Engineering, RAG Systems
The novel — Technical Communication, Decision Making
The pattern — LLM/NLP Foundations, Prompt Engineering, RAG Systems, Agentic Systems, LLM Deployment (+2 more)
The situation — Prompt Engineering, RAG Systems
The Speculative Decoding Insight — LLM Deployment, Performance
The takeaway — Prompt Engineering, RAG Systems, Reliability
Theoretical Foundations — Agentic Systems, Vision & Document AI, Reliability
throughput — AI Engineering Landscape, Python for AI, LLM/NLP Foundations, Prompt Engineering, LLM Deployment (+13 more)
token — AI Engineering Landscape, Python for AI, ML Fundamentals, First LLM App, LLM/NLP Foundations (+24 more)
tokenization — AI Engineering Landscape, LLM/NLP Foundations, Prompt Engineering, RAG Systems, Audio & Speech (+5 more)
Tool & Framework Reference — Python for AI, Orchestration Frameworks, Observability & Guardrails, Performance
Tool Recommendations: As of January 2026 — Orchestration Frameworks, Observability & Guardrails
tool use — AI Engineering Landscape, First LLM App, Prompt Engineering, Agentic Systems, Orchestration Frameworks (+5 more)
top-k — ML Fundamentals, LLM/NLP Foundations, Prompt Engineering, RAG Systems, Orchestration Frameworks (+1 more)
top-p — ML Fundamentals, LLM/NLP Foundations, Prompt Engineering
Traces — System Design, Performance
transformer — AI Engineering Landscape, Python for AI, ML Fundamentals, First LLM App, LLM/NLP Foundations (+15 more)
Type Safety — Orchestration Frameworks, Observability & Guardrails
U
Unresolved Questions — Technical Communication, Decision Making
V
Vaswani et al. (2017), “Attention Is All You Need” — AI Engineering Landscape, ML Fundamentals, LLM/NLP Foundations
vector search — AI Engineering Landscape, ML Fundamentals, First LLM App, RAG Systems, Orchestration Frameworks (+4 more)
Visual concepts — Vision & Document AI, Video & Multimodal
W
What happened — Prompt Engineering, RAG Systems, Reliability, Cost Engineering
What people do — Prompt Engineering, RAG Systems, Agentic Systems, LLM Deployment, Security (+1 more)
What people do: — LLM/NLP Foundations, Prompt Engineering, Orchestration Frameworks, Observability & Guardrails, Cloud AI Providers (+13 more)
What You’ll Learn — AI Engineering Landscape, Python for AI, ML Fundamentals, First LLM App, LLM/NLP Foundations (+24 more)
When it fails — RAG Systems, Responsible AI
When to Use What — Orchestration Frameworks, Observability & Guardrails
Why it fails — Prompt Engineering, RAG Systems, Agentic Systems, LLM Deployment, Security (+1 more)
Why it fails: — LLM/NLP Foundations, Prompt Engineering, Orchestration Frameworks, Observability & Guardrails, Cloud AI Providers (+13 more)
Why it works — Prompt Engineering, System Design
Why Quantization Works — LLM Deployment, Performance
Why This Chapter Matters — AI Engineering Landscape, Decision Making
Y
Yao et al. (2022), “ReAct: Synergizing Reasoning and Acting” — Prompt Engineering, Agentic Systems
Z
zero-shot — Prompt Engineering, Vision & Document AI
Zheng et al. (2023), “Judging LLM-as-a-Judge” — ML Fundamentals, Backend Engineering, MLOps & Evaluation