Generative AI for Business — Week 8

Final Presentations

Week 8

JHU Carey Business School | 2026
Generative AI for Business — Week 8

Today's agenda

Time Topic
0:00–0:05 Logistics + presentation order
0:05–2:30 Final presentations
2:30–2:45 Break
2:45–3:00 Course wrap-up + what's next
JHU Carey Business School | 2026
Generative AI for Business — Week 8

Presentation order

Slot Team Project
1
2
3
4
5
6
7
8
JHU Carey Business School | 2026
Generative AI for Business — Week 8

Presentation format reminder

    ┌─────────────────────────────────────────────────────┐
    │                                                      │
    │  12 MINUTES PRESENTATION                             │
    │  ┌──────────────────────────────────────────────┐   │
    │  │ Problem & motivation              ~2 min     │   │
    │  │ Approach & architecture            ~2 min     │   │
    │  │ Demo                               ~4 min     │   │
    │  │ Evaluation results                 ~2 min     │   │
    │  │ Governance & takeaways             ~2 min     │   │
    │  └──────────────────────────────────────────────┘   │
    │                                                      │
    │  3 MINUTES Q&A                                       │
    │  ┌──────────────────────────────────────────────┐   │
    │  │ Questions from class + instructor             │   │
    │  └──────────────────────────────────────────────┘   │
    │                                                      │
    │  ⏱ Hard stop at 15 minutes. Practice your timing.   │
    └─────────────────────────────────────────────────────┘
JHU Carey Business School | 2026
Generative AI for Business — Week 8

Evaluation rubric

    ┌─────────────────────────────────────────────────────┐
    │                                                      │
    │  Technical implementation              30%           │
    │  ┌─────────────────────────────────────────────┐    │
    │  │ Does it work? Well-structured code?          │    │
    │  │ Course concepts applied correctly?           │    │
    │  │ Commit history shows iteration?              │    │
    │  └─────────────────────────────────────────────┘    │
    │                                                      │
    │  Problem & approach                    20%           │
    │  ┌─────────────────────────────────────────────┐    │
    │  │ Well-defined problem? Justified approach?    │    │
    │  │ Design decisions explained?                  │    │
    │  └─────────────────────────────────────────────┘    │
    │                                                      │
    │  Evaluation rigor                      20%           │
    │  ┌─────────────────────────────────────────────┐    │
    │  │ Systematic testing? Honest results?          │    │
    │  │ Failures documented?                         │    │
    │  └─────────────────────────────────────────────┘    │
    │                                                      │
    │  Governance & responsibility           15%           │
    │  ┌─────────────────────────────────────────────┐    │
    │  │ Risks identified? Guardrails built?          │    │
    │  │ Ethical considerations addressed?            │    │
    │  └─────────────────────────────────────────────┘    │
    │                                                      │
    │  Presentation & communication          15%           │
    │  ┌─────────────────────────────────────────────┐    │
    │  │ Clear demo? Well-structured talk?            │    │
    │  │ Good use of time? Strong Q&A?                │    │
    │  └─────────────────────────────────────────────┘    │
    └─────────────────────────────────────────────────────┘
JHU Carey Business School | 2026
Generative AI for Business — Week 8

As an audience member

    ┌─────────────────────────────────────────────────────┐
    │                                                      │
    │  GOOD QUESTIONS TO ASK:                              │
    │                                                      │
    │  Technical                                           │
    │  • "What happens when [edge case]?"                  │
    │  • "Why did you choose [approach] over [alternative]?"│
    │  • "What was your biggest technical challenge?"       │
    │                                                      │
    │  Evaluation                                          │
    │  • "How did you measure [quality dimension]?"         │
    │  • "What was your failure rate on [task type]?"       │
    │                                                      │
    │  Business / Governance                               │
    │  • "How would this scale to [larger use case]?"      │
    │  • "What's the cost per query in production?"        │
    │  • "What happens if a user tries to misuse this?"    │
    │                                                      │
    │  Reflection                                          │
    │  • "What would you do differently with more time?"   │
    │  • "What surprised you most during the project?"     │
    │                                                      │
    └─────────────────────────────────────────────────────┘
JHU Carey Business School | 2026
Generative AI for Business — Week 8

Presentations

JHU Carey Business School | 2026
Generative AI for Business — Week 8

Break

15 minutes

JHU Carey Business School | 2026
Generative AI for Business — Week 8

Course Wrap-up

JHU Carey Business School | 2026
Generative AI for Business — Week 8

What we covered

    Week 1                              Week 2
    FOUNDATIONS                          ECOSYSTEM
    ┌──────────────────┐               ┌──────────────────┐
    │ Transformers,     │               │ Foundation models,│
    │ attention,        │──────────────►│ open vs closed,  │
    │ diffusion         │               │ model selection  │
    └──────────────────┘               └────────┬─────────┘
                                                │
    Week 3                              Week 4  │
    REASONING & CONTEXT                 AGENTS  ▼
    ┌──────────────────┐               ┌──────────────────┐
    │ CoT, reasoning   │               │ RAG, tool use,   │
    │ models, context  │──────────────►│ agent loop,      │
    │ engineering      │               │ architectures    │
    └──────────────────┘               └────────┬─────────┘
                                                │
    Week 5                              Week 6  ▼
    MULTI-AGENT & MCP                   GOVERNANCE
    ┌──────────────────┐               ┌──────────────────┐
    │ Orchestration,   │               │ Risk, evaluation,│
    │ MCP, reliability,│──────────────►│ regulation,      │
    │ AgentRx          │               │ red-teaming      │
    └──────────────────┘               └────────┬─────────┘
                                                │
                                        Week 7-8▼
                                        PROJECTS
                                       ┌──────────────────┐
                                       │ Build, evaluate, │
                                       │ present, reflect │
                                       └──────────────────┘
JHU Carey Business School | 2026
Generative AI for Business — Week 8

Key takeaways

    ┌─────────────────────────────────────────────────────┐
    │                                                      │
    │  1. CONTEXT ENGINEERING > MODEL SELECTION             │
    │     How you use the model matters more than which    │
    │     model you pick                                   │
    │                                                      │
    │  2. EVALUATION IS NOT OPTIONAL                       │
    │     If you can't measure it, you can't improve it   │
    │     or trust it                                      │
    │                                                      │
    │  3. AGENTS ARE POWERFUL BUT FRAGILE                  │
    │     Cascading failures, reliability trade-offs,      │
    │     human-in-the-loop is still essential             │
    │                                                      │
    │  4. GOVERNANCE IS A DESIGN REQUIREMENT               │
    │     Not an afterthought. Build it in from day one.  │
    │                                                      │
    │  5. THE FIELD IS MOVING FAST                        │
    │     What you learned this semester is a foundation.  │
    │     The specific tools will change. The principles   │
    │     won't.                                           │
    │                                                      │
    └─────────────────────────────────────────────────────┘
JHU Carey Business School | 2026
Generative AI for Business — Week 8

Where GenAI is heading

    NOW (2026)                          NEXT 12-24 MONTHS
    ┌──────────────────────┐      ┌──────────────────────────┐
    │                      │      │                          │
    │ Text + image + code  │ ───► │ Full multimodal          │
    │ are strong           │      │ (video, 3D, robotics)    │
    │                      │      │                          │
    │ Agents need          │ ───► │ More autonomous agents   │
    │ human-in-the-loop    │      │ with better reliability  │
    │                      │      │                          │
    │ MCP is early         │ ───► │ Standard agent protocol  │
    │                      │      │ (like HTTP for agents)   │
    │                      │      │                          │
    │ Evaluation is        │ ───► │ Standardized eval        │
    │ ad hoc               │      │ frameworks + benchmarks  │
    │                      │      │                          │
    │ Regulation forming   │ ───► │ Compliance requirements  │
    │                      │      │ become concrete          │
    └──────────────────────┘      └──────────────────────────┘
JHU Carey Business School | 2026
Generative AI for Business — Week 8

Keep learning

    ┌─────────────────────────────────────────────────────┐
    │                                                      │
    │  STAY CURRENT                                        │
    │  • Anthropic blog, OpenAI blog, Google AI blog      │
    │  • arXiv cs.CL (NLP) and cs.AI (general AI)        │
    │  • Simon Willison's blog (practical GenAI)          │
    │  • The Gradient, Import AI (newsletters)            │
    │                                                      │
    │  KEEP BUILDING                                       │
    │  • Claude Code is free to experiment with            │
    │  • Build tools for your actual work                  │
    │  • Contribute to open-source AI projects            │
    │                                                      │
    │  GO DEEPER                                           │
    │  • Karpathy's "Neural Networks: Zero to Hero"       │
    │  • Stanford CS224N (NLP with deep learning)         │
    │  • fast.ai (practical deep learning)                │
    │  • Anthropic research papers                         │
    │                                                      │
    └─────────────────────────────────────────────────────┘
JHU Carey Business School | 2026
Generative AI for Business — Week 8

Reminders

    ┌─────────────────────────────────────────────────────┐
    │                                                      │
    │  DUE TODAY (if not already submitted):               │
    │                                                      │
    │  [ ] Code repository — final commit pushed           │
    │  [ ] Write-up — 2-3 pages, PDF                       │
    │  [ ] Peer review — confidential, individual          │
    │                                                      │
    │  COURSE EVALUATIONS                                  │
    │  [ ] Please fill out course evaluations              │
    │      Your feedback directly shapes future offerings  │
    │                                                      │
    └─────────────────────────────────────────────────────┘
JHU Carey Business School | 2026
Generative AI for Business — Week 8

Thank you

It's been a great semester.

Now go build something.

JHU Carey Business School | 2026

This is it. Eight weeks of foundations, models, reasoning, agents, and governance — all leading to this. Today you show us what you built. Have fun with it.

Tight schedule today. Each team gets 15 minutes total: 12 min presentation + 3 min Q&A. We'll go straight through with short transitions. Break after all presentations, then we wrap up the course.

Fill this in before class. Either randomize or let teams volunteer for order. First slot is hardest, last slot benefits from seeing others. Consider randomizing to keep it fair.

Hard stop at 15 minutes — it's not fair to other teams if you go over. Practice your timing beforehand. The most common mistake is spending too long on background and rushing through the demo and evaluation. The demo is the highlight — give it space.

This is the same rubric from the project description. I'm showing it again so it's fresh in everyone's mind while watching presentations. When I'm evaluating, I'm looking at all five dimensions. The biggest differentiator is usually evaluation rigor — teams that systematically tested their system and honestly reported results (including failures) score significantly higher than teams with flashy demos but no evaluation.

Encourage students to ask substantive questions. Good Q&A makes the whole session more valuable. The reflection questions often lead to the most interesting answers. Remind students: engagement during presentations is part of their participation grade.

Transition to presentations. Call up the first team. Keep time strictly.

Let's take a step back and see the full arc. We started with how these models work (Week 1), then which ones to use (Week 2), then how to use them well (Week 3), then how to make them act in the world (Weeks 4-5), then how to do it responsibly (Week 6), and finally you built something real (Weeks 7-8). Each week built on the previous one. The projects you just presented integrate concepts from across the entire course.

Five things I want you to remember a year from now. First: context engineering is the highest-leverage skill — the same model with better context dramatically outperforms a bigger model with lazy prompting. Second: always evaluate systematically — gut feel is not enough for production. Third: agents are the future but they need guardrails — fully autonomous AI is not here yet. Fourth: governance isn't bureaucracy, it's engineering discipline. Fifth: the specific models and tools you used this semester will be obsolete within a year. The concepts — attention, context engineering, agentic patterns, evaluation, governance — will last much longer.

What to watch. Multimodal is expanding beyond text and images into video, 3D, and eventually robotics. Agent reliability is the key bottleneck — expect rapid progress here. MCP or something like it will become the standard way agents connect to tools, just like HTTP standardized web communication. Evaluation will mature from ad-hoc testing to standardized frameworks. And regulation will move from frameworks to enforceable requirements. If you stay in this space, these are the trends that will define the next few years.

This course gave you a foundation. To stay sharp: follow the blogs and newsletters for what's new, keep building with Claude Code on real problems, and go deeper if you want to understand the internals. The best way to learn GenAI is to use it every day. Find a workflow in your job or personal life where AI can help, and iterate on it. That's how you build real fluency.

Final logistics. Make sure all deliverables are submitted. Peer review is individual and confidential — be honest about contributions. And please fill out course evaluations. This is a new course and your feedback is critical for improving it next year.

Close it out. Thank the students for their work, the TAs if applicable, the guest speaker. Remind them that the skills they built here are immediately applicable. Encourage them to keep building.