HIGH-YIELD REVISION GUIDE & CHEAT SHEET
AI Agents & Advanced RAG Systems
Complete Semester Guide
High-Yield Comprehensive Guide, ReAct Execution Traces, RRF Hybrid Search
Calculations, Planning DAGs & Quick-Cram Appendix
Artificial Intelligence & LLM Application Engineering | Course Code: University Of California -
Berkeley - CS 294 / CS 194 | 2024-2025 Comprehensive Edition
📘 WHAT’S INSIDE THIS GUIDE:
✔ Autonomous Agent Cognitive Systems: Perception, Task Planning, Vector Memory, and Tool
Sandboxing
✔ Reasoning & Execution: Step-by-step multi-turn execution trace of the ReAct (Thought-Action-
Observation) paradigm
✔ Advanced RAG Engineering: Step-by-step worked trace of Reciprocal Rank Fusion (RRF)
blending Dense and BM25 candidate lists
✔ Agentic Planning Frameworks: Plan-and-Solve DAG decompositions vs. Tree of Thoughts (ToT)
heuristic state evaluations
✔ Self-Reflection & Heuristic Learning: The Reflexion episodic memory architecture and self-
correction prompting
✔ Multi-Agent Orchestration: Supervisor-Worker architectures, Context Distillation, and preventing
loop deadlocks
✔ 10 Deadly Agent & RAG Engineering Traps (Lost-in-the-Middle, chunk boundary severance,
infinite execution cycles)
✔ APPENDIX: 1-Hour Emergency Pre-Exam Quick-Cram Cheat Sheet with cognitive components
table and 25 active recall flashcards
, Artificial Intelligence & LLM Application Engineering ·AI Agents & Advanced RAG Systems Complete Semester
University Of California - Berkeley - CS 294 / CS 194 Guide
Disclaimer: This is an independently created academic study aid. It is not affiliated with, endorsed by, or sponsored by any specific
university, textbook author, or publisher.
Independent Study Aid. Not affiliated with or endorsed by any specific university or Page 2 of 7
publisher.
AI Agents & Advanced RAG Systems
Complete Semester Guide
High-Yield Comprehensive Guide, ReAct Execution Traces, RRF Hybrid Search
Calculations, Planning DAGs & Quick-Cram Appendix
Artificial Intelligence & LLM Application Engineering | Course Code: University Of California -
Berkeley - CS 294 / CS 194 | 2024-2025 Comprehensive Edition
📘 WHAT’S INSIDE THIS GUIDE:
✔ Autonomous Agent Cognitive Systems: Perception, Task Planning, Vector Memory, and Tool
Sandboxing
✔ Reasoning & Execution: Step-by-step multi-turn execution trace of the ReAct (Thought-Action-
Observation) paradigm
✔ Advanced RAG Engineering: Step-by-step worked trace of Reciprocal Rank Fusion (RRF)
blending Dense and BM25 candidate lists
✔ Agentic Planning Frameworks: Plan-and-Solve DAG decompositions vs. Tree of Thoughts (ToT)
heuristic state evaluations
✔ Self-Reflection & Heuristic Learning: The Reflexion episodic memory architecture and self-
correction prompting
✔ Multi-Agent Orchestration: Supervisor-Worker architectures, Context Distillation, and preventing
loop deadlocks
✔ 10 Deadly Agent & RAG Engineering Traps (Lost-in-the-Middle, chunk boundary severance,
infinite execution cycles)
✔ APPENDIX: 1-Hour Emergency Pre-Exam Quick-Cram Cheat Sheet with cognitive components
table and 25 active recall flashcards
, Artificial Intelligence & LLM Application Engineering ·AI Agents & Advanced RAG Systems Complete Semester
University Of California - Berkeley - CS 294 / CS 194 Guide
Disclaimer: This is an independently created academic study aid. It is not affiliated with, endorsed by, or sponsored by any specific
university, textbook author, or publisher.
Independent Study Aid. Not affiliated with or endorsed by any specific university or Page 2 of 7
publisher.
