Generative AI for Business — Week 7

Guest Speaker + Project Workshop

Week 7

JHU Carey Business School | 2026
Generative AI for Business — Week 7

Today's agenda

Time Topic
0:00–0:05 Housekeeping
0:05–0:50 Guest speaker: SZNS CEO
0:50–1:05 Q&A
1:05–1:20 Break
1:20–2:20 Progress demos (5 min per team)
2:20–2:55 Project work time + office hours
2:55–3:00 Next week: what to prepare
JHU Carey Business School | 2026
Generative AI for Business — Week 7

Housekeeping

Due this week:

  • Assignment 5 (submitted)
  • Progress demo (today, in class)

Due next week (Week 8):

  • Final presentation (12 min + 3 min Q&A)
  • Demo (live or pre-recorded video, 3-5 min)
  • Code repository (GitHub — commit history matters)
  • Write-up (2-3 pages)
  • Peer review (confidential, individual)
JHU Carey Business School | 2026
Generative AI for Business — Week 7

Guest Speaker

SZNS CEO

GenAI in Production

JHU Carey Business School | 2026
Generative AI for Business — Week 7

Questions for the speaker

Think about:

  • What was the hardest part of going from prototype to production?
  • How do you handle hallucination and reliability at scale?
  • What's your evaluation and monitoring setup?
  • How do you think about build vs. buy for AI components?
  • What would you do differently if starting over today?

Take notes — these insights are directly applicable to your final projects

JHU Carey Business School | 2026
Generative AI for Business — Week 7

Break

15 minutes

JHU Carey Business School | 2026
Generative AI for Business — Week 7

Progress Demos

5 minutes per team

JHU Carey Business School | 2026
Generative AI for Business — Week 7

Demo format

    ┌─────────────────────────────────────────────────────┐
    │              5-MINUTE PROGRESS DEMO                   │
    │                                                       │
    │  1. WHAT YOU'RE BUILDING             (~1 min)        │
    │     Problem statement + project option                │
    │                                                       │
    │  2. SHOW WHAT WORKS                  (~2 min)        │
    │     Live demo or screenshots of current state        │
    │                                                       │
    │  3. WHAT'S LEFT                      (~1 min)        │
    │     Remaining work for next week                     │
    │                                                       │
    │  4. WHERE YOU'RE STUCK               (~1 min)        │
    │     Blockers, open questions, help needed            │
    │                                                       │
    └─────────────────────────────────────────────────────┘

This is informal. Show real state, not polish.

JHU Carey Business School | 2026
Generative AI for Business — Week 7

Feedback framework

When watching other teams, think about:

    ┌─────────────────────────────────────────────────────┐
    │                                                      │
    │  ✓  What's working well?                             │
    │     (technical approach, UX, evaluation plan)        │
    │                                                      │
    │  ?  What's unclear?                                  │
    │     (problem definition, architecture, scope)        │
    │                                                      │
    │  ⚠  What risks do you see?                          │
    │     (too ambitious, missing evaluation, governance)  │
    │                                                      │
    │  💡 Suggestions                                      │
    │     (tools, approaches, simplifications)             │
    │                                                      │
    └─────────────────────────────────────────────────────┘
JHU Carey Business School | 2026
Generative AI for Business — Week 7

Project Work Time

+ Office Hours

JHU Carey Business School | 2026
Generative AI for Business — Week 7

Common issues at this stage

    SCOPE CREEP                     EVALUATION GAP
    ┌──────────────────────┐       ┌──────────────────────┐
    │ "We added three more │       │ "It works but we     │
    │  features and now    │       │  haven't tested it   │
    │  nothing works"      │       │  systematically"     │
    │                      │       │                      │
    │ FIX: Cut scope.      │       │ FIX: Write 15 test   │
    │ One thing that works │       │ queries NOW. Run     │
    │ beats three that     │       │ eval before next     │
    │ don't.               │       │ week.                │
    └──────────────────────┘       └──────────────────────┘

    DEMO ANXIETY                    GOVERNANCE AFTERTHOUGHT
    ┌──────────────────────┐       ┌──────────────────────┐
    │ "What if the API     │       │ "We haven't thought  │
    │  fails during the    │       │  about risks yet"    │
    │  live demo?"         │       │                      │
    │                      │       │ FIX: Add a           │
    │ FIX: Pre-record a    │       │ governance section   │
    │ video backup. Always.│       │ to your write-up.    │
    │                      │       │ It's 15% of grade.   │
    └──────────────────────┘       └──────────────────────┘
JHU Carey Business School | 2026
Generative AI for Business — Week 7

Final deliverables checklist

    ┌─────────────────────────────────────────────────────┐
    │  DUE NEXT WEEK                                       │
    │                                                       │
    │  [ ] Demo (live or pre-recorded video, 3-5 min)      │
    │      → Recommended: record a backup video             │
    │                                                       │
    │  [ ] Presentation (12 min + 3 min Q&A)               │
    │      → Problem, approach, architecture, demo,         │
    │        evaluation results, governance                  │
    │                                                       │
    │  [ ] Code repository (GitHub)                         │
    │      → Commit history matters — commit early & often  │
    │      → Include a README with setup instructions       │
    │                                                       │
    │  [ ] Write-up (2-3 pages)                             │
    │      → Problem, design decisions, evaluation,         │
    │        limitations, governance reflection              │
    │                                                       │
    │  [ ] Peer review (confidential, individual)           │
    │      → Assess each team member's contributions        │
    └─────────────────────────────────────────────────────┘
JHU Carey Business School | 2026
Generative AI for Business — Week 7

Presentation structure suggestion

    ┌─────────────────────────────────────────────────────┐
    │  12 MINUTES                                          │
    │                                                       │
    │  0:00  Problem & motivation              (~2 min)    │
    │        Why does this matter? Who is the user?        │
    │                                                       │
    │  2:00  Approach & architecture            (~2 min)    │
    │        What did you build? How does it work?         │
    │                                                       │
    │  4:00  Demo                               (~4 min)    │
    │        Show it working. Highlight key features.      │
    │                                                       │
    │  8:00  Evaluation results                 (~2 min)    │
    │        How did you test it? What did you find?       │
    │                                                       │
    │  10:00 Governance & limitations           (~1 min)    │
    │        Risks, guardrails, what you'd do differently  │
    │                                                       │
    │  11:00 Takeaways                          (~1 min)    │
    │        What did you learn?                            │
    │                                                       │
    │  12:00 Q&A                                (~3 min)    │
    └─────────────────────────────────────────────────────┘
JHU Carey Business School | 2026
Generative AI for Business — Week 7

Rubric reminder

    ┌───────────────────────────────────┬────────┐
    │ Category                          │ Weight │
    ├───────────────────────────────────┼────────┤
    │ Technical implementation          │  30%   │
    │ Does it work? Is code solid?      │        │
    ├───────────────────────────────────┼────────┤
    │ Problem & approach                │  20%   │
    │ Well-defined? Well-motivated?     │        │
    ├───────────────────────────────────┼────────┤
    │ Evaluation rigor                  │  20%   │
    │ Systematic testing? Honest results│        │
    ├───────────────────────────────────┼────────┤
    │ Governance & responsibility       │  15%   │
    │ Risks considered? Guardrails?     │        │
    ├───────────────────────────────────┼────────┤
    │ Presentation & communication      │  15%   │
    │ Clear demo? Well-structured talk? │        │
    └───────────────────────────────────┴────────┘

Honest failures score better than hidden problems

JHU Carey Business School | 2026
Generative AI for Business — Week 7

See you next week

Come ready to present

JHU Carey Business School | 2026

Today is different — no lecture. First half: a guest speaker who's building with GenAI in production. Second half: your time to work on final projects with instructor support. Every team will give a 5-minute progress demo and get feedback.

Quick logistics. Assignment 5 should already be submitted. Today's progress demo is informal — show what you have, get feedback. Next week is the real deal: full presentations, final deliverables, everything due. Let's make sure everyone knows what's expected.

Introduce the speaker. Brief bio, what SZNS does, why their experience is relevant to what we've been learning. Let the speaker take it from here.

Prompt students to think about questions before the talk starts. These questions map directly to course concepts: production challenges (Week 4-5), reliability (Week 5), evaluation (Week 6), model selection (Week 2). Encourage students to connect what they hear to their own projects.

The demo should be honest, not polished. Show what actually works. Show what doesn't. The point is to get feedback while there's still time to act on it. I want to see real code running, not mockups. If something is broken, show the broken thing — the class might be able to help debug it. Each team gets 5 minutes with 2-3 minutes for feedback from the class and me.

Good feedback is specific and actionable. Not "looks good" — instead "the RAG retrieval seems solid but I'm not sure how you'll evaluate hallucination." Encourage students to give honest, constructive feedback. This is a collaborative session, not a competition.

These are the four most common issues I see at this point. Scope creep: you got ambitious and now you're spread thin — cut features, not quality. Evaluation gap: your system works on the demo case but you haven't tested it broadly — write test cases today. Demo anxiety: APIs are unpredictable — record a backup video. Governance afterthought: remember it's 15% of your grade — even a paragraph on risks and mitigations helps.

Walk through the checklist. Emphasize: record a backup video even if you plan to demo live. Commit history matters — if you dump everything in one commit the night before, we'll notice. The write-up should be honest about limitations and failures. Peer review is confidential — be honest about contributions.

This is a suggested structure, not required. The demo should be the centerpiece — 4 minutes of the 12. Don't spend too long on motivation or background. We know the context. Show us what you built, how well it works, and what you learned. The governance section is short but important — show you've thought about it.

Review the rubric one more time. Technical implementation is the largest bucket but evaluation rigor is a close second at 20%. An impressive demo with no systematic evaluation will score lower than a simpler system with thorough testing. Governance is 15% — don't skip it. And remember: honest documentation of failures and limitations is valued. We'd rather see "we tried X, it didn't work because Y, so we pivoted to Z" than a polished surface hiding fundamental issues.