Agentic Artificial Intelligence for Information Systems Graduate Academic Certificate

Course Description

This course provides a comprehensive overview of AI tools designed for a diverse audience of students, researchers, and teachers with a focus on practical, real-world use of contemporary tools. The curriculum, grounded in the user-centric principles of Information Science, focuses on the practical application and ethical implications of contemporary AI technologies. Participants will be introduced to a range of tools for natural language processing (NLP), machine learning (ML), and data analytics, with a specific emphasis on how these technologies can be leveraged for enhanced learning, scholarly communication, and information management. The course will address the entire lifecycle of AI tool use, from data collection and model selection to ethical deployment and critical evaluation of outputs. By providing hands-on experience and fostering a foundational understanding of AI's capabilities and limitations, this program aims to equip students with the knowledge to effectively and responsibly integrate AI tools into their academic and professional practices.

Course Objectives and Learning Outcomes

Upon successful completion of this course, students will be able to:

• Explain the AI Lifecycle: Describe and practice the end-to-end lifecycle of an AI tool, from data collection, annotation, and model selection to deployment, monitoring, and critical evaluation.
• Apply Contemporary AI Tools: Utilize contemporary natural language processing (NLP), machine learning (ML), and data-analytics tools to collect, preprocess, and analyze data to solve authentic academic and professional problems.
• Design Human-Centered Systems: Architect AI systems and workflows that empower users, prioritize fairness, ensure transparency, and respect human values.
• Critically Evaluate AI Outputs & Models: Critically assess outputs generated by AI models, identifying their capabilities, operational boundaries, algorithmic biases, and factual inaccuracies.
• Analyze AI Ethics & Societal Impacts: Apply foundational principles of information ethics to AI deployment, addressing fairness, accountability, transparency, data security, privacy, and accessibility across educational and research environments.
• Develop AI Literacy & Prompt Engineering: Master prompt-engineering strategies and AI-literacy techniques to interact effectively with conversational agents while embedding critical inquiry into production workflows.
• Lead Collaborative User-Centric Projects: Collaborate effectively in multidisciplinary teams to design, implement, test, and present a functional AI-assisted tool or workflow alongside actionable policy recommendations.

Course Format

This course is delivered in an interactive, 16-week face-to-face seminar and laboratory format. Instructional sessions blend foundational lectures on information science and AI lifecycle principles with hands-on computer lab exercises. Students participate in live tool demonstrations, collaborative problem sets, structured weekly discussion circles on AI ethics and human-centered design, and team-based development studios where they prototype and evaluate user-centric AI workflows.

Course Description

This course explores the theory, design, and implementation of Human-Centered Artificial Intelligence (HCAI) systems—AI technologies that are designed to be reliable, safe, trustworthy, and aligned with human needs. The course will introduce design principles, review mainstream AI techniques, and examine the development of AI-driven applications that prioritize user control and user values. Through hands-on projects, discussions, and real-world case studies, students will explore how to design, implement, and evaluate AI systems that are trustworthy and effectively responsive to human needs. The course is structured into four major segments: (1) The Human-Centered AI Framework, (2) Design Metaphors for Human-AI Interaction, (3) Foundations of AI & Rationale for Human-Centered Approaches, and (4) Recent Advances in Human-Centered AI Applications.

Course Outcomes

Upon successful completion of this course, students will be able to:

• Understand Foundational HCAI Concepts: Articulate core human-centered AI philosophies (rationalism vs. empiricism) and explain their fundamental importance in designing reliable, safe, and trustworthy systems.
• Survey and Deploy Mainstream AI Techniques: Understand application scenarios for machine learning, deep learning, and large language models (LLMs), and deploy them effectively within human-aligned architectures.
• Architect Trustworthy Systems with Balanced Control: Design and implement AI applications using two-dimensional frameworks that simultaneously balance high levels of human control with high levels of automation.
• Analyze Interaction Metaphors: Investigate and evaluate different paradigms for AI systems (e.g., intelligent agents, teammates, social robots) and assess their implications for usability, ethics, and societal impact.
• Evaluate Fairness, Transparency, and Bias: Critically evaluate AI algorithms and models for explainability, interpretability, usability, and algorithmic bias across sensitive domains such as health, communication, and education.
• Develop Practical HCAI Applications: Utilize programming environments and modern model APIs to develop functional, human-centered AI applications addressing documented user needs.
• Synthesize and Communicate Research Insights: Review cutting-edge human-centered AI literature, deliver critical research presentations, and author comprehensive technical design reports.

Course Format

This course adopts a 16-week blended teaching model that bridges theoretical rigor and practical engineering. Systematic instruction on core HCAI frameworks, design metaphors, and machine learning models is complemented by active student-led case study presentations and collaborative discussions. Students engage in iterative project development studios where they translate conceptual HCAI principles into working code repositories, supported by structured milestone reviews and peer critiques.

Course Description

This course introduces students to the foundational concepts and practical applications of a collaborative methodology for rapid information system prototyping using AI. Moving beyond traditional programming syntax, this approach focuses on using natural language and high-level conceptual prompts to iteratively develop and refine functional systems. Participants learn how to effectively partner with large language models (LLMs), multimodal models (MMMs), and code-generation tools to accelerate the prototyping lifecycle from initial ideation to working software. The curriculum emphasizes the development of 'algorithmic intuition'—the ability to steer, critique, and debug AI-generated code and system behaviors. Ethical considerations, code provenance, accountability, and user-centered design remain central themes as students evaluate the technical boundaries and proper use cases of AI-driven prototyping.

Course Objectives and Learning Outcomes

Upon successful completion of this course, students will be able to:

• Contrast Development Paradigms: Define and explain vibe coding, contrasting AI-assisted, prompt-driven prototyping with traditional manual programming and legacy software workflows.
• Formulate Vibe Coding Methodology: Apply structured natural language and multimodal prompts to guide AI models through the end-to-end prototyping lifecycle of functional information systems.
• Develop Algorithmic Intuition: Cultivate practitioner intuition to steer, critically evaluate, and refine code and architecture generated by LLMs and code assistants.
• Select and Integrate Tool Stacks: Evaluate and select appropriate generative AI platforms (text, visual, code engines) tailored to specific information system requirements and integration constraints.
• Audit AI-Generated Code: Critically evaluate AI-generated scripts and systems for accuracy, security, algorithmic coherence, and alignment with user experience goals.
• Address Ethical, Legal, and Provenance Boundaries: Analyze ethical considerations, accountability, code provenance, and demographic bias inherent in generative systems, recognizing the operational boundaries between prototypes and enterprise production systems.
• Deliver Human-Centered Prototypes: Collaborate to design, document, and present functional, AI-assisted information system prototypes that solve authentic real-world challenges while preserving user trust.

Course Format

This course is delivered in an experiential, 16-week studio-and-lab format focused on hands-on creation and real-time critique. Classes are organized around live system-building demonstrations, guided prompt-refinement workshops, and collaborative rapid-prototyping sprints. Students actively build with modern generative code and UI platforms, moving iteratively from natural language prompts to interactive interfaces, supplemented by weekly peer reviews, reflective technical essays, and a capstone studio showcase.

Note: 
INFO 5715 requires completion of INFO 5701.

Course Description

This course explores the principles and practices of designing systems where humans and multiple AI agents collaborate to achieve complex goals. Moving beyond single-agent interaction, the curriculum focuses on multi-agent system (MAS) architectures and communication protocols, including inter-agent protocols (e.g., Agent2Agent) and supervisory oversight mechanisms (e.g., Model Context Protocol / MCP). Students will learn to design, prototype, and evaluate both user experience (UX) and agent experience (AX) to blend human insight with the computational power of AI agents. Key topics include task decomposition, agent negotiation, conflict resolution, and the creation of auditable interfaces for transparency and system oversight. Through hands-on projects, students develop a critical understanding of the technical challenges and ethical considerations involved in building and directing multi-agent systems.

Course Objectives and Learning Outcomes

Upon successful completion of this course, students will be able to:

• Explain Multi-Agent System Architectures: Articulate the operational differences, communication structures, and behavioral characteristics of centralized, distributed, and emergent multi-agent systems (MAS).
• Apply Foundational Protocols: Implement standardized multi-agent protocols, including Agent2Agent for inter-agent collaboration and Model Context Protocol (MCP) for human supervisory direction.
• Manage and Orchestrate Agent Workflows: Decompose complex organizational tasks into human and agent subtasks, establish role delegation strategies, and resolve operational conflicts among collaborating agents.
• Design for Dual Experiences (UX & AX): Prototype and evaluate user experience (UX) and agent experience (AX), balancing autonomous agent execution with meaningful, intuitive human governance.
• Build Transparent and Auditable Interfaces: Design and prototype auditable interfaces and explainability dashboards that provide human operators with verifiable oversight, monitoring, and corrective control.
• Evaluate Ethical, Societal, and Safety Risks: Critically analyze vulnerabilities, failure modes, accountability gaps, and trust dynamics in autonomous multi-agent environments.
• Prototype Functional Multi-Agent Systems: Develop, document, and present a functional multi-agent prototype integrating two or more specialized agents operating cooperatively under human direction.

Course Format

This course is conducted in an interactive, 16-week seminar-laboratory format combining foundational architectural lectures with hands-on orchestration workshops. In-class activities include protocol simulation labs, agent-role negotiation exercises, and participatory design sessions focused on supervisor interfaces. Students work individually and in small teams to configure agent communication flows and test multi-agent interactions, concluding with an interactive design studio and showcase where teams demonstrate their working multi-agent prototypes.

Note: 
INFO 5719 requires completion of INFO 5715.