705.625.8VL - Introduction to Agentic AI

Course Structure

Module Preparation Activities (13 total)

• Replacing traditional module discussions, students will complete module preparation activities for each of the 13 modules.

• These activities are designed to motivate and contextualize the upcoming material, helping students ground themselves before lecture.

• Deliverables will be low-stakes but essential for engagement and continuity across the course.

Homework Assignments (4 total)

• There will be four summative homework assignments, each spanning three modules.

• Homework will balance theory and application, requiring students to both analyze concepts and implement solutions.

• Assignments will use Python and relevant agentic frameworks (e.g., LangGraph, CrewAI) to reinforce practical skills alongside conceptual rigor.

Module Review Questions

• Each module will include a short set of review questions.

• These provide an opportunity for students to self-assess comprehension and reinforce key takeaways from lectures.

Final Programming Assignment

• The course culminates in a final programming project in which students design and implement their own agentic system.

• This capstone assignment integrates concepts, techniques, and frameworks covered throughout the course, demonstrating students’ mastery of both foundational theory and practical implementation.

Course Topics

• Introduction to Agentic AI

• Agent Theory

• Agent Architectures

• Environments and Rationality

• Decision Making in Agents

• Uncertain Knowledge and Reasoning

• Learning and Adaptation

• Game Theory

• Multiagent Systems I

• Observability

• Generative Agent Modeling

• Agentic RAG

• Reasoning Models as an Agentic System

• State of the Art (SOTA) in Agentic AI

Course Goals

By the end of this course, students will be able to explain the foundational principles of agentic AI and analyze agent–environment interactions using formal models. They will design and evaluate agent architectures and multi-agent systems, apply performance metrics to simulated environments, and critically assess emerging generative agent frameworks based on their memory, planning, and interaction capabilities.

1. Describe the foundational principles of agentic AI, including the roles of autonomy, perception-action loops, and rational behavior in intelligent agents.
2. Analyze agent-environment interactions using formal models such as decision trees, utility functions, and Markov decision processes.
3. Design simple agent architectures and multi-agent systems that incorporate learning, decision-making, and communication protocols.
4. Evaluate agent behaviors in simulated environments using performance metrics, reward trajectories, and policy analysis.
5. Compare and critique emerging generative agent frameworks (e.g., LLM/VLM-based agents) based on their capabilities in memory, reflection, planning, and interaction.

Textbooks

There are no required textbooks for this course. Optional readings will be presented in individual modules and will be accessible via Johns Hopkins libraries.

">

• Stuart J. Russell and Peter Norvig, Artificial Intelligence: A Modern Approach, 4th Edition, Prentice Hall, 2020.

Required Software

• Python (latest stable release, recommended 3.11+)

• LangGraph (for agentic workflows and orchestration)

• Ollama (for running and experimenting with local LLMs)

Student Coursework Requirements

This course emphasizes both conceptual understanding and practical implementation of agentic AI. Students will engage in weekly preparation activities, graded assignments, review questions, and a final programming project.

Attendance in this live, synchronous course is required. Each unexcused absence beyond the first will result in an overall course grade reduction of half a letter grade.

• Module Preparation Activities (20%)

  • Completion of Activities (10%): Weekly module preparation activities must be posted to the discussion board by Tuesday at 7:00 PM EST prior to class.

  • In-Class Sharing (10%): Each student must volunteer to share their preparation activity work at least twice during the semester (5% each). Sharing should be clear, concise, and relevant.

  • Activities are graded primarily on completion and timeliness; late or missing submissions will not receive full credit.

• Homework Assignments (40%)

  • There will be four summative homework assignments, each spanning three modules.

  • Assignments will combine theory and application, requiring both written analysis and practical coding.

  • Work will be implemented in Python using frameworks such as LangGraph and CrewAI.

  • Evaluation will emphasize technical accuracy, clarity of reasoning, code functionality, and proper use of frameworks.

• Module Review Questions (20%)

  • Each module includes a short set of review questions.

  • These are auto-graded in Canvas, with up to three attempts allowed.

  • The questions reinforce comprehension of key concepts and prepare students for larger assignments.

• Final Programming Assignment (20%)

  • The course culminates in a final programming project where students design and implement their own agentic system.

  • The project integrates course concepts, including architectures, decision-making, reasoning, and generative frameworks.

  • Deliverables will include runnable code, supporting documentation, and a short written explanation of design choices and system behavior.

Students should expect to dedicate 7–10 hours per week to this course:

• 1–2 hours: Additional reading as assigned by the instructor

• 3 hours: Attendance at live virtual sessions

• 3–5 hours: Assignments, module preparation activities, and review questions

Course Policies

Generative AI tools may be used in this course, but only as a supplementary resource, not a replacement, for your own work. You are expected to apply your own foundational knowledge, particularly in Python, and use AI tools responsibly to support coding and idea generation. All submitted work must demonstrate your own analysis, reasoning, and understanding. Submissions that are clearly generated without meaningful student contribution will be graded accordingly.

Academic Policies

Deadlines for Adding, Dropping and Withdrawing from Courses

Students may add a course up to one week after the start of the term for that particular course. Students may drop courses according to the drop deadlines outlined in the EP academic calendar (https://ep.jhu.edu/student-services/academic-calendar/). Between the 6th week of the class and prior to the final withdrawal deadline, a student may withdraw from a course with a W on their academic record. A record of the course will remain on the academic record with a W appearing in the grade column to indicate that the student registered and withdrew from the course.

Academic Misconduct Policy

All students are required to read, know, and comply with the Johns Hopkins University Krieger School of Arts and Sciences (KSAS) / Whiting School of Engineering (WSE) Procedures for Handling Allegations of Misconduct by Full-Time and Part-Time Graduate Students. This policy prohibits academic misconduct, including but not limited to the following: cheating or facilitating cheating; plagiarism; reuse of assignments; unauthorized collaboration; alteration of graded assignments; and unfair competition. Course materials (old assignments, texts, or examinations, etc.) should not be shared unless authorized by the course instructor. Any questions related to this policy should be directed to EP’s academic integrity officer at ep-academic-integrity@jhu.edu.

Students with Disabilities - Accommodations and Accessibility

Johns Hopkins University is committed to providing welcoming, equitable, and accessible educational experiences for all students. If disability accommodations are needed for this course, students should request accommodations through Student Disability Services (SDS) as early as possible to provide time for effective communication and arrangements.  For further information about this process, please refer to the SDS Website.

Student Conduct Code

The fundamental purpose of the JHU regulation of student conduct is to promote and to protect the health, safety, welfare, property, and rights of all members of the University community as well as to promote the orderly operation of the University and to safeguard its property and facilities. As members of the University community, students accept certain responsibilities which support the educational mission and create an environment in which all students are afforded the same opportunity to succeed academically.  For a full description of the code please visit the following website: https://studentaffairs.jhu.edu/policies-guidelines/student-code/

Classroom Climate

JHU is committed to creating a classroom environment that values the diversity of experiences and perspectives that all students bring. Everyone has the right to be treated with dignity and respect. Fostering an inclusive climate is important. Research and experience show that students who interact with peers who are different from themselves learn new things and experience tangible educational outcomes. At no time in this learning process should someone be singled out or treated unequally on the basis of any seen or unseen part of their identity.    If you have concerns in this course about harassment, discrimination, or any unequal treatment, or if you seek accommodations or resources, please reach out to the course instructor directly. Reporting will never impact your course grade. You may also share concerns with your program chair, the Assistant Dean for Diversity and Inclusion, or the Office of Institutional Equity. In handling reports, people will protect your privacy as much as possible, but faculty and staff are required to officially report information for some cases (e.g. sexual harassment).

Course Auditing

When a student enrolls in an EP course with “audit” status, the student must reach an understanding with the instructor as to what is required to earn the “audit.” If the student does not meet those expectations, the instructor must notify the EP Registration Team [EP-Registration@exchange.johnshopkins.edu] in order for the student to be retroactively dropped or withdrawn from the course (depending on when the "audit" was requested and in accordance with EP registration deadlines). All lecture content will remain accessible to auditing students, but access to all other course material is left to the discretion of the instructor.