Agentic AI — Course

B.Sc. Applied Computer Science (UAS) · lecture + lab · 15 weeks (+ optional capstone).

Agentic AI systems combine language models with tools, memory, and autonomous loops. This course builds them from first principles — foregrounding the mathematics and algorithms / data structures — before any framework.

Contents (preliminary syllabus)

Status: Alpha

Part I — Foundations

Wk Topic Lecture Exercises
1 Introduction to Agents & the Training Ladder lecture html - ipynb
2 The ReAct Loop & Tool Use lecture

Part II — Reasoning & Planning

Wk Topic Lecture Exercises
3 Task Decomposition & Agent Domains
4 Tree-of-Thoughts & Search
5 Agents as Markov Decision Processes

Part III — Model & Data

Wk Topic Lecture Exercises
6 Embeddings & Vector Arithmetic
7 Inside the Model: Tokenization, Attention & Context Window
8 Vector Databases & (Agentic) RAG
9 Sessions, Memory & Compaction

Part IV — Systems & Orchestration

Wk Topic Lecture Exercises
10 State Machines & Workflow Orchestration
11 Multi-Agent Systems & Game Theory

Part V — Safety, Ops & Wrap-up

Wk Topic Lecture Exercises
12 Gateway, Security & Guardrails
13 Observability & Evaluation
14 Exam Preparation & Review
15 Outlook & Ethics

Capstone (optional / outlook)

Wk Topic Lecture Exercises
16 Agentic Software Development (capstone) —

Literature & further reading

Agentic patterns & engineering

  • Gulli, A. (2025). Agentic Design Patterns. Springer — the pattern catalogue this course maps to (prompt chaining, routing, parallelization, reflection, …); see glossary § Agentic design patterns.
  • Lakshmanan, V.; Hapke, H. (2025). Generative AI Design Patterns: Solutions to Common Challenges When Building GenAI Agents and Applications. O'Reilly.
  • Huyen, C. (2025). AI Engineering: Building Applications with Foundation Models. O'Reilly.
  • Albada, M. (2025). Building Applications with AI Agents: Designing and Implementing Multiagent Systems. O'Reilly — German ed.: KI-Agenten entwickeln: Entwurf, Implementierung, Monitoring (transl. F. Langenau, dpunkt.verlag, 2026).

Multi-agent, protocols & MCP

  • Dibia, V. (2025). Designing Multi-Agent Systems: Principles, Patterns, and Implementation for AI Agents. Self-published — multiagentbook.com.
  • Lanham, M. (2026). AI Agents in Action (2nd ed.). Manning — MCP & A2A protocols.
  • Shoham, Y.; Leyton-Brown, K. (2009). Multiagent Systems: Algorithmic, Game-Theoretic, and Logical Foundations. Cambridge University Press — the standard MAS textbook; full text free at masfoundations.org (W11).
  • Arsanjani, A.; Bustos, J. P. (2026). Agentic Architectural Patterns for Building Multi-Agent Systems. Packt — agentic patterns, RAG, LLMOps, enterprise-scale systems (W8, W11, W13).

Foundations & "inside the LLM"

  • Russell, S.; Norvig, P. (2021). Artificial Intelligence: A Modern Approach (4th ed.). Pearson — classical-AI foundations: intelligent agents, search ($A^*$, W3–4), sequential decisions / MDPs (W5), and Multiagent Decision Making (Ch. 18; Ch. 17 in the Global Edition — game theory; W11).
  • Sutton, R. S.; Barto, A. G. (2018). Reinforcement Learning: An Introduction (2nd ed.). MIT Press — finite MDPs, returns & value functions, Bellman equations (W5).
  • Raschka, S. (2024). Build a Large Language Model (From Scratch). Manning — attention, tokenization, KV-cache (W7).
  • Alammar, J.; Grootendorst, M. (2024). Hands-On Large Language Models: Language Understanding and Generation. O'Reilly — vector spaces & embeddings (W6).

Frameworks & agentic software engineering

  • Oshin, M.; Campos, N. (2025). Learning LangChain: Building AI and LLM Applications with LangChain and LangGraph. O'Reilly — graph-based state machines (W10).
  • Hassan, A. E., et al. (2025). Agentic Software Engineering: Foundational Pillars and a Research Roadmap. arXiv:2509.06216 — the SASE framework (capstone, W16).
  • Hassan, A. E., et al. (2026). Agentic Software Engineering (book) — companion to the SASE paper (capstone, W16).