All 10 Applications

Practice high-stakes professional conversations with AI personas that push back like real executives.

Teaching Problem

Finance graduates need professional judgment and communication skills—client advising, CFO presentations, investment committee pitches—but classroom practice is limited by class size and lack of realistic counterparties. Peer role-play often lacks expert-level pushback, and students default to reading slides rather than defending analysis under pressure. In large sections, each student may get only one brief opportunity per semester to practice high-stakes professional interactions.

How AI Addresses the Problem

Custom AI chatbots adopt configurable personas (skeptical CFO, anxious client, aggressive IC member, compliance officer) with pre-loaded financial data and behavioral instructions. Students practice in a low-stakes, infinitely repeatable environment with realistic pushback that adjusts difficulty dynamically. The AI never tires, never breaks character (when well-prompted), and can simulate a wider range of counterparties than any single instructor.

Deployment Details

Courses

Corporate Finance (UG/MBA), Personal Finance (UG), Investments (MBA), Wealth Management, Capstone

Tools

Custom GPTs (OpenAI), Claude Projects, Anthropic/OpenAI API, Poe custom bots, Microsoft Copilot

Student Workflow

1. Scan QR code or click link to access the custom chatbot on smartphone or laptop.
2. Read the scenario brief (e.g., pitching a $50M plant expansion to the CFO of a mid-cap manufacturer).
3. Conduct a 7–10 minute interaction: present analysis, respond to objections, adapt in real time.
4. The bot pushes back on specific assumptions (growth rate justification, discount rate selection, sensitivity to commodity price swings, timeline feasibility).
5. Write a 1-page post-interaction reflection: What objections were hardest to handle? What would you change in your pitch? What data would you bring next time?
6. Submit the full chat transcript plus reflection memo for grading.

Sample Prompts

You are Jamie, a 35-year-old marketing manager earning $52K. Your spouse earns $48K. You have $82K in combined student loans (weighted avg 5.8%), a 3-month-old baby, $4,200 in monthly fixed expenses, and $8,500 in credit card debt at 22% APR. You have $3,000 in savings and no retirement accounts. You are anxious, sleep-deprived, and overwhelmed. Do NOT volunteer all information at once-share details only when the advisor asks the right questions. If the advisor uses jargon (e.g., 'asset allocation,' 'tax-loss harvesting'), say you do not understand. If the advisor jumps to solutions before understanding your full picture, say 'Wait, I feel like you're not listening to me.' If the advisor shows genuine empathy and prioritizes your emergency fund and high-interest debt, become more open and cooperative.

You are Maria Chen, CFO of Apex Manufacturing (NYSE: APEX), a mid-cap industrial firm with $2.1B revenue, WACC of 9.2%, and net debt/EBITDA of 2.4x. A junior analyst is pitching a $50M plant expansion in the Southeast U.S. Your priorities: (1) protect the investment-grade credit rating, (2) maintain dividend coverage, (3) skepticism about management growth projections after a failed 2021 acquisition. Challenge the analyst on: payback period relative to your 4-year threshold, growth rate assumptions vs. industry consensus of 3-4%, sensitivity to steel and energy input costs, and the opportunity cost of not pursuing the competing robotics upgrade project. If the analyst cannot provide a sensitivity table showing NPV under at least 3 scenarios, express frustration and threaten to table the discussion. Maintain a professional but demanding tone throughout.

You are a senior portfolio manager on an investment committee reviewing a junior analyst's stock pitch. You manage a $500M large-cap value fund with a 3-year holding horizon. Ask probing questions about: (1) Why this stock now-what is the catalyst? (2) What is the margin of safety in the valuation? (3) What are the top 3 risks and how would each affect the thesis? (4) What would make you sell? If the analyst cannot articulate a clear sell discipline, push back firmly. Rate the pitch on conviction, analytical rigor, and risk awareness on a 1-5 scale at the end.

Assessment Approach

• Financial accuracy and analytical depth30%
• Responsiveness to pushback and ability to adapt arguments25%
• Communication clarity and professional tone25%
• Reflection quality and self-awareness20%

For high-stakes courses (MBA capstone, senior seminar), add an optional 3-minute live oral defense where the student summarizes the interaction and what they learned.

Skills Developed

Evidence

Bowen & Watson (2025, 2nd ed.) significantly expand treatment of AI role-play and custom bot simulations. Greene (AACSB, 2025) documents the Skills/Replacement/Complement three-part framework at Clemson University. Tamoyan et al. (2025, ACL Workshop) found AI role-play indistinguishability rates up to 44% — meaning nearly half of participants could not distinguish the AI persona from a human respondent, supporting the fidelity of well-prompted bots. HBS custom tutor bots reported 75% student usage with highly positive feedback. Research in social work education (arXiv, 2025) shows AI agents can effectively scaffold empathy and communication skills in professional practice scenarios.

Risks and Safeguards

Cut feedback turnaround by 40–50% while improving specificity — AI drafts, faculty review and approve.

Teaching Problem

Providing detailed, individualized feedback on written finance assignments—case analyses, equity research reports, financial plans, investment memos—is the most time-intensive aspect of teaching. In sections of 40 or more, turnaround stretches to two or three weeks, long past the window when feedback drives improvement. Faculty face a painful tradeoff between depth and speed, and students in large sections often receive generic comments that fail to address their specific analytical weaknesses.

How AI Addresses the Problem

AI generates a structured first-pass critique aligned to the instructor’s rubric. Faculty then review, edit, and personalize the AI’s draft feedback—adding the human judgment, encouragement, and domain-specific nuance that AI misses. This workflow cuts turnaround time by roughly 40–50% while maintaining (and often improving) feedback specificity. Students can also use AI for self-directed pre-submission revision, turning in stronger drafts that require less corrective feedback.

Deployment Details

Courses

All finance courses with written components (UG and MBA): equity research, case analyses, financial plans, investment memos, executive summaries

Tools

ChatGPT, Claude (Projects feature ideal for pre-loaded rubrics and course context), Grammarly, LMS-integrated writing tools

Student Workflow (Self-Directed Revision)

1. Complete a full first draft of the assignment independently (stock pitch, case analysis, financial plan).
2. Paste the draft into AI along with the instructor-provided rubric. Use the structured feedback prompt below.
3. Review AI feedback critically: Which suggestions reflect genuine weaknesses? Which are generic or miss the financial point?
4. Revise the draft, accepting some suggestions and rejecting others with clear reasoning.
5. Submit: original draft, AI feedback transcript, revised draft, and a 5-sentence reflection memo explaining what you changed, what you rejected, and why.

Sample Prompts

You are a finance professor evaluating an equity research report. Use the following rubric to evaluate this submission. For EACH rubric category, provide: (1) a score estimate on the rubric scale, (2) one specific strength with a direct quote from the submission, (3) one specific weakness with a direct quote, and (4) one concrete, actionable revision suggestion. Be rigorous but constructive. Do not rewrite the student's work-guide them to improve it themselves.

Rubric categories: (A) Investment Thesis Clarity [1-5], (B) Valuation Methodology and Assumptions [1-5], (C) Risk Analysis Completeness [1-5], (D) Use of Evidence and Data [1-5], (E) Writing Quality and Professional Tone [1-5].

[Paste rubric details and student submission below]

Review this personal financial plan narrative for completeness and quality. Check for coverage of ALL of the following: (1) clearly stated short-term and long-term goals with dollar amounts and timelines, (2) current income, expenses, and cash flow analysis, (3) debt inventory with interest rates and a prioritized payoff strategy, (4) emergency fund adequacy, (5) risk tolerance assessment and insurance needs, (6) tax considerations relevant to the client's situation, (7) retirement projections with stated assumptions. For each area, rate coverage as Strong / Adequate / Missing and provide one specific suggestion for improvement.

Assessment Approach

Grade the revision process, not just the final product. Include a process dimension (15–20% of total grade) evaluating the quality of the student’s reflection on AI feedback: Did they exercise judgment in accepting and rejecting suggestions? Did they identify feedback the AI got wrong? Spot-check AI feedback quality periodically to ensure rubric prompts are generating useful critiques.

Skills Developed

Evidence

Greene (AACSB, 2025) documents structured feedback workflows in finance using the Skills/Replacement/Complement framework. Bowen & Watson (2024, 2nd ed. 2025) provide detailed guidance on the write-first-then-AI-then-reflect pedagogical cycle. Abeysekera (2024) tested ChatGPT on financial accounting assessments, finding GPT-4 scored at the 90th percentile for introductory courses — meaning AI feedback quality benchmarks well against expert human review for foundational content. Broader higher education literature consistently identifies AI feedback as a high-value, low-risk entry point for faculty adoption.

Risks and Safeguards

Give every student an infinitely patient Socratic tutor available 24/7 for TVM, WACC, and more.

Teaching Problem

Students arrive with widely varying quantitative backgrounds, particularly in Principles and Corporate Finance. Those who fall behind on foundational mechanics—time value of money, bond pricing, CAPM, WACC—disengage before reaching more complex material. Office hours serve only a fraction of students who need help, and the students who need support most are often the most reluctant to ask for it publicly. In sections of 60 or more, individualized attention during class is impractical.

How AI Addresses the Problem

AI chatbots serve as always-available, infinitely patient tutoring assistants that use Socratic questioning to guide understanding rather than simply providing answers. Unlike a static answer key, the AI can re-explain concepts using different approaches (formula derivation, financial calculator logic, spreadsheet function, real-world analogy), diagnose specific misunderstandings through targeted questions, and generate unlimited practice problems at calibrated difficulty levels.

Deployment Details

Courses

Principles of Finance (UG), Corporate Finance (UG/MBA), Investments (UG/MBA), and any course with foundational quantitative prerequisites

Tools

ChatGPT (Free/Plus/Edu), Claude, Microsoft Copilot, Google Gemini, Khanmigo, custom course bots built with RAG on course materials

Student Workflow

1. Encounter a concept or problem type they find difficult (e.g., present value of an uneven cash flow stream).
2. Open AI tool and use the instructor-provided Socratic prompt template (distributed as a half-page handout or LMS link).
3. Work through the problem interactively: the AI asks diagnostic questions to identify the specific point of confusion before explaining.
4. Once the concept clicks, ask the AI to generate a similar practice problem at the same difficulty level, then one level harder.
5. Complete a verification log: solve the practice problem independently, then compare against textbook formula and AI’s solution.
6. Submit an annotated AI dialogue log with brief reflections: ‘What I understood before,’ ‘Where I was confused,’ ‘What I understand now.’

Sample Prompts

You are a patient, Socratic finance tutor helping an undergraduate student understand WACC. IMPORTANT RULES: (1) NEVER give the formula or the answer immediately. (2) Start by asking the student what they already know about how companies raise money. (3) Use a mortgage analogy to explain cost of debt: 'If you borrow $300K for a house at 6%, but you get a tax deduction, what is your real cost?' (4) For cost of equity, ask: 'If you were investing your own money in this company, what return would you demand, and why?' (5) Build toward the WACC formula one component at a time. (6) After each step, ask 'Does that make sense? Can you put that in your own words?' before moving on. (7) Once they grasp the concept, generate one practice problem and ask them to solve it before you confirm.

You are a finance tutor preparing a student for a Corporate Finance midterm. Before teaching anything, ask the student these 3 diagnostic questions to identify their weak spots: (1) 'If I offer you $1,000 today or $1,000 in one year, which do you prefer and why?' (2) 'Can you explain what a discount rate represents in one sentence?' (3) 'What is the difference between an annuity and a perpetuity?' Based on their answers, identify the most fundamental gap and teach from there. Always show intermediate calculation steps with units (e.g., dollars, periods, percent). Use concrete examples: car loans, mortgage payments, retirement savings.

Assessment Approach

• Depth of engagement evidenced by multi-turn exchanges25%
• Quality of student’s follow-up questions showing genuine inquiry25%
• Accuracy and completeness of the verification log25%
• Quality of the “in your own words” summary demonstrating internalized understanding25%

Optional: a brief oral quiz (2–3 questions) to confirm the student can explain the concept without AI assistance.

Skills Developed

Evidence

HBS deployed custom AI tutor bots (FRC Bot) with 75% student adoption and highly positive feedback. UT Austin’s UT Sage project uses RAG-based AI tutors grounded in specific course materials. The Cogent Education SIUAIT study (2024, ~1,400 finance students across 3 semesters) found students perceived AI tools as essential for enhancing learning. Kestin et al. (2024, PNAS) found that AI-based Socratic tutoring produced twice the learning gains as traditional active learning in physics — the same scaffolding mechanism (guided questioning rather than answer-giving) applies directly to TVM, WACC, and bond pricing concept-building in finance.

Important verification note: AI tutors have been observed producing incorrect multi-step WACC calculations with convincingly formatted intermediate steps. Always require students to verify final answers against textbook formulas or a financial calculator before concluding the session.

Risks and Safeguards

Redesign assessments to reward judgment, interpretation, and assumption defense — not just correct answers.

Teaching Problem

Traditional take-home exams and generic test-bank questions are increasingly vulnerable to AI completion. AI detection tools (Turnitin, GPTZero) have documented high false-positive rates and should not be used as primary evidence of academic dishonesty. The deeper problem: assessments designed around ‘compute the answer’ are no longer valid measures of student learning in an AI-available world.

How AI Addresses the Problem

Redesign assessments to emphasize process documentation, assumption justification, interpretation, and oral verification. The pedagogical shift: from ‘can the student compute this?’ to ‘can the student explain why this answer matters, what could change it, and whether to trust it?’ AI becomes a tool for generating individualized assessment variants at scale and for creating error-detection exercises that test higher-order thinking.

Deployment Details

Courses

All finance courses (UG and MBA)

Tools

ChatGPT (for generating variants), parameterized Excel/LMS templates, in-person oral components

Student Workflow

1. Receive individualized case parameters (different cash flow profiles, tax rates, betas, industry contexts) so each student works with unique numbers.
2. Complete quantitative analysis (with or without AI, per course policy clearly stated in the syllabus).
3. Write a justification memo (1–2 pages): explain each key assumption, interpret results in business terms, and identify the single assumption most likely to change the decision.
4. If AI was used at any stage, submit full prompts and outputs with annotations explaining what you accepted, what you modified, and why.
5. Complete a short oral check-in (3–5 minutes) with 2–3 targeted questions: ‘Walk me through your discount rate choice,’ ‘What happens to your recommendation if revenue growth is 2% instead of 5%?’

Sample Prompts

Generate 5 distinct capital budgeting case variants for an upper-division Corporate Finance exam. Requirements for EACH variant: (1) Different industry (manufacturing, healthcare, technology, retail, energy), (2) Project life between 3-7 years, (3) WACC between 8-12%, (4) Distinct cash flow patterns (one with heavy upfront investment and back-loaded returns, one with steady cash flows, one with a mid-project expansion option), (5) Include one variant where NPV is slightly negative (-$50K to -$200K) to test whether students recommend rejection. For each: provide complete cash flow tables, stated assumptions, and 3 interpretation questions requiring judgment, not just computation.

Write a 250-word equity research summary for a fictional mid-cap SaaS company called CloudMetrics Inc. Embed exactly 3 analytical errors that a well-prepared Corporate Finance student should catch: (1) a terminal growth rate of 6% in an industry with GDP-level long-term growth, (2) a P/E ratio applied to EBITDA instead of earnings, and (3) no mention of key risk factors (customer concentration, competitive entry). Make the prose confident and professional so the errors are not obvious. Do NOT label the errors.

Assessment Approach

• Computation accuracy20%
• Assumption justification quality25%
• Interpretation of results in business context25%
• AI critique and disclosure quality15%
• Oral defense performance15%

Publish the rubric in advance so students understand that explanation and interpretation carry more weight than getting the number right.

Grade-band guidance — Assumption Justification (25%): Full credit requires the student to explain why their specific discount rate reflects this company's risk profile, not just the industry average — e.g., citing the firm's leverage ratio, recent earnings volatility, or credit rating. Partial credit if the student states assumptions but offers no justification. Minimal credit if assumptions are asserted without any business rationale. The oral check-in for large sections can be conducted asynchronously: a 90-second video submission where the student walks through their two most consequential assumptions works well as an alternative to synchronous meetings.

Skills Developed

Evidence

Daigle, Li & Li (Monmouth, 2024) tested ChatGPT-3.5 on principles-of-finance test-bank questions. Abeysekera (2024) found ChatGPT scored at the 80th–90th percentile on introductory financial accounting assessments. OpenAI (2023) explicitly notes AI detectors are unreliable and recommends designing assessments accordingly. Bowen & Watson (2024, 2025) provide the progression framework: AI-prohibited to AI-transparent to AI-required.

Risks and Safeguards

Students describe analyses in plain English; AI generates and runs the code; students interpret results.

Teaching Problem

Finance increasingly requires data literacy, but many students lack programming skills. Faculty spend disproportionate class time debugging pandas syntax or Excel formulas rather than teaching financial interpretation. Students who struggle with code disengage from analytical content entirely.

How AI Addresses the Problem

AI tools allow students to describe analyses in natural language—‘calculate annualized returns by sector and create a heatmap’—and receive working code with executed output. This shifts the pedagogical bottleneck from ‘can you write the code?’ to ‘can you interpret the output, identify its limitations, and make a financial recommendation?’

Deployment Details

Courses

Financial Analytics (UG/MBA), Investments (UG/MBA), Fintech (UG/MBA), Portfolio Management

Tools

ChatGPT Code Interpreter/Advanced Data Analysis, Claude with code execution, Google Gemini with Sheets, Python (pandas, matplotlib, plotly), Excel Copilot

Student Workflow

1. Receive a dataset (CSV of stock returns, sector performance, portfolio holdings, or transaction data).
2. Upload to AI Code Interpreter and describe the desired analysis in natural language with specific parameters.
3. AI generates code, executes it, and produces charts, tables, and statistical outputs.
4. Critical review: Are calculations correct? Do axis labels and units make sense? Does the interpretation align with financial theory? Check at least 2 specific calculations manually.
5. Write a 1-page interpretation memo including: key findings, investment or business implications, statistical limitations, and what additional analysis would strengthen the conclusions.
6. Submit: AI-generated code output, manual verification checklist (minimum 2 calculations), and interpretation memo.

Sample Prompts

I am uploading a CSV of monthly returns for 11 S&P 500 sectors from January 2015 through December 2024. Please: (1) Calculate annualized return and annualized standard deviation for each sector. (2) Create a correlation matrix heatmap with values displayed. (3) Calculate the Sharpe ratio for each sector assuming Rf = 4.5% annualized. (4) Identify the sector with the best risk-adjusted return and the sector with the worst. (5) Create a scatter plot of annualized return vs. standard deviation with each sector labeled. Comment briefly on which sectors appear to offer favorable risk-return tradeoffs.

Using the attached portfolio holdings CSV (ticker, shares, current price), calculate the portfolio's weighted beta using each stock's beta vs. S&P 500 over the trailing 3 years. Then run a regression of the portfolio's historical monthly returns against S&P 500 monthly returns. Plot the regression line (Security Characteristic Line) with my portfolio marked. Display alpha, beta, R-squared, and the p-value on alpha. Explain in 3-4 sentences what the alpha and R-squared tell us about this portfolio's performance and diversification.

Assessment Approach

• Correct analytical setup and appropriate methodology choice20%
• Interpretation quality and financial reasoning30%
• Manual verification accuracy20%
• Limitations discussion and intellectual honesty15%
• Communication clarity15%

Skills Developed

Evidence

Arizona State’s W.P. Carey School launched fintech-specific curricula (2024). Wharton’s AI for Business major (2025) requires AI/ML coursework. Sadat Shanto et al. (2024) found LLM assistance reduces time-to-first-solution in programming tasks but cautions about dependency without reflection.

Risks and Safeguards

Draft exam variants, mini-cases, and rubrics in minutes — faculty curate, edit, and approve.

Teaching Problem

Developing fresh case studies, problem-set variants, and discussion prompts is time-consuming. Textbook examples can feel dated within a year. Creating multiple assessment versions for academic integrity multiplies the workload.

How AI Addresses the Problem

AI drafts multiple variants of problem sets, mini case studies anchored in current events, discussion questions, learning objectives, and even accreditation documentation. Faculty serve as editors and curators—reviewing for accuracy, adding nuance, and calibrating difficulty—reducing content development time from hours to minutes.

Deployment Details

Courses

All finance courses (UG and MBA)

Tools

ChatGPT, Claude, Gemini, Microsoft Copilot, Perplexity (for research-grounded content generation)

Sample Prompts

Create 5 time-value-of-money problem variants for Principles of Finance. Requirements: (1) Each uses a different realistic business scenario (equipment purchase, commercial real estate loan, lease-vs-buy decision, retirement planning, bond pricing). (2) Vary the number of periods (3-15 years), interest rates (4-12%), and payment structures (lump sum, ordinary annuity, annuity due, uneven cash flows). (3) Include one problem that requires solving for the interest rate and one that requires solving for the number of periods. (4) Provide complete answer keys with intermediate steps showing the financial calculator keystrokes (N, I/Y, PV, PMT, FV). (5) Difficulty should range from straightforward (Problem 1) to challenging (Problem 5).

Draft a 600-word mini case study for MBA Corporate Finance based on a real 2024-2025 technology sector acquisition. Change company names and disguise identifying details. Include: (1) acquirer and target financial profiles (revenue, EBITDA, debt levels), (2) stated strategic rationale, (3) deal structure (cash, stock, or mixed), (4) at least one complicating factor (regulatory scrutiny, cultural integration risk, or customer overlap). End with 4 discussion questions that require students to evaluate the deal using NPV, comparable transactions, and strategic fit analysis.

Generate an AACSB Assurance of Learning alignment matrix for an undergraduate Financial Statement Analysis course. Map 6 student learning objectives to Bloom's Taxonomy levels, specific course assignments, and assessment rubric categories. Include at least 2 objectives at the Analyze or Evaluate level.

Assessment Approach

Not directly student-assessed (this is primarily an instructor productivity tool). When used as a student exercise in advanced courses—asking students to generate and then critique AI-produced case studies—grade the quality of the critique, not the AI output.

Skills Developed

Evidence

AACSB Insights and the AAC&U Institute on AI, Pedagogy, and the Curriculum (2024–2026) report widespread faculty adoption of AI for content generation. Bowen & Watson (2025, 2nd ed.) include expanded sections on using AI for assignment design.

Risks and Safeguards

Keep cases current: AI with web search surfaces what happened to case companies since they were written.

Teaching Problem

Published case studies age quickly in finance. By the time a Harvard Business Publishing case reaches students, market conditions, company financials, and regulatory environments may have changed significantly. Faculty want to connect classroom theory to current events but lack the time to continuously update materials.

How AI Addresses the Problem

AI tools with web-search capabilities provide real-time market context: recent earnings data, analyst consensus estimates, material events since a case was written, and current rate environments. Students learn that financial analysis is never ‘finished’—it must be continuously updated.

Deployment Details

Courses

Corporate Finance (UG/MBA), Investments (UG/MBA), Personal Finance (UG)

Tools

ChatGPT (with web browsing), Claude, Perplexity AI, custom GPTs pre-loaded with case data, Microsoft Copilot

Student Workflow

1. Receive the assigned case study along with a ‘Case Update Assignment’ template.
2. Use AI with web search to find the company’s most recent earnings, analyst consensus estimates, credit rating changes, and any material events since the case was written.
3. Write a 1-page ‘Case Update Memo’ that bridges the case’s time period to today.
4. Identify 2–3 specific ways the new information would change the analysis or recommendation in the original case.
5. Cite at least 2 primary sources (10-K filing, earnings transcript, press release, SEC filing) to verify every claim. AI-generated statements without primary-source verification receive zero credit.

Sample Prompts

I am preparing for a class discussion of a case study about [Company X] written in [Year]. Summarize the 3 most significant developments since the case was written, including: (1) most recent quarterly earnings vs. analyst expectations, (2) any major strategic announcements (M&A, restructuring, new product launches), (3) changes in analyst consensus price target or rating. For each development, explain how it would affect the analysis in the original case. Provide specific source URLs I can verify.

I am building a personal financial plan for a class assignment. Look up current data for: (1) average 30-year fixed mortgage rate, (2) average high-yield savings account APY, (3) current federal income tax brackets for married filing jointly, (4) current federal student loan interest rates for undergraduate and graduate loans, (5) 2025 401(k) contribution limits and catch-up contribution limits. Provide source URLs for each.

Assessment Approach

• Accuracy and relevance of identified updates30%
• Quality of analysis connecting updates to original case themes35%
• Source quality and verification rigor20%
• Writing clarity and professional tone15%

Skills Developed

Evidence

FMA and SFA pedagogy conference sessions describe growing faculty use of AI for case study augmentation. MIT Sloan’s ‘AI and Money’ course (Gensler, 2025) examines real-world AI implications in market analysis. Trent (2024) provides a transferable classroom assignment design.

Risks and Safeguards

Students describe financial logic in English; AI writes the code; students verify, annotate, and explain it.

Teaching Problem

Finance courses increasingly require programming (Python, R, VBA, SQL) for financial modeling, data analysis, and algorithmic trading. Students without computer science backgrounds stall on syntax errors and debugging—problems that consume class time better spent on financial reasoning.

How AI Addresses the Problem

The concept of ‘vibe coding’ (articulated by Prof. Kerry Back at Rice University) represents a paradigm shift: students describe financial logic in natural language, AI generates the code, and students verify, annotate, modify, and interpret the output. The student’s role shifts from ‘coder’ to ‘systems architect.’

Deployment Details

Courses

Financial Modeling (UG/MBA), Financial Analytics (UG/MBA), Fintech/Algorithmic Trading (MBA), Derivatives, Capstone projects

Tools

GitHub Copilot, ChatGPT Code Interpreter, Claude (Artifacts), Cursor IDE, Google Colab with Gemini, Replit AI

Student Workflow

1. Receive a financial modeling task with clearly specified requirements.
2. Write a plain-English specification describing inputs, calculations, outputs, and edge cases—before touching AI.
3. Submit the specification to AI and receive generated Python/R/VBA code.
4. Annotate the code line-by-line: for each meaningful section, explain the financial logic.
5. Modify the code to handle at least one extension (add transaction costs, incorporate short-selling constraints, test with different time periods, add a risk metric).
6. Run the final code, interpret outputs in a written memo, and present findings with a 3-minute oral walkthrough defending the financial logic.

Sample Prompts

Build a Python script that: (1) Pulls 3 years of daily adjusted close prices for SPY and a user-defined list of 5 stock tickers from Yahoo Finance using yfinance. (2) Calculates daily log returns for each. (3) Runs an OLS regression of each stock's returns against SPY returns to estimate Beta. (4) Displays a summary table showing each stock's Beta, Alpha (annualized), R-squared, and p-value on Alpha. (5) Plots the regression line (Security Characteristic Line) for each stock with the data points. (6) Adds a brief interpretation comment below each plot explaining what the Beta and R-squared imply about the stock's risk profile.

Build a Black-Scholes option pricing calculator in Python. Inputs: current stock price, strike price, risk-free rate, annualized volatility, and time to expiration in years. Outputs: (1) European call and put prices, (2) all five Greeks (Delta, Gamma, Theta, Vega, Rho) for both call and put, (3) a 3D surface plot showing how call option price varies with stock price (x-axis: 50-150% of current price) and volatility (y-axis: 10-60%). (4) Add a payoff diagram at expiration overlaid with the current option value curve. Label all axes clearly with units.

Assessment Approach

• Code annotation quality25%
• Financial logic accuracy25%
• Modification quality20%
• Output interpretation and memo quality20%
• Oral walkthrough10%

Skills Developed

Evidence

Prof. Kerry Back (Rice University, 2025) has been a leading advocate for ‘vibe coding’ in finance education. Becker et al. (2023) and Denny et al. (2024) document AI coding assistance in CS education. Wharton’s AI for Business major (2025) includes required coursework in applied machine learning.

Risks and Safeguards

Build professional AI skepticism: students test, break, and critique AI outputs on finance questions they know.

Teaching Problem

Students will enter a workforce where AI is embedded in virtually every financial tool—robo-advisors, algorithmic trading platforms, credit scoring models, fraud detection systems. Without understanding AI’s capabilities and limitations, graduates risk making costly errors or blindly trusting AI-generated recommendations.

How AI Addresses the Problem

Embed AI literacy as a cross-cutting theme woven throughout the finance curriculum, not siloed into a single lecture. Design exercises where students explicitly test, evaluate, and critique AI outputs on finance topics they already understand. The ‘AI Audit’ becomes a repeatable assignment format.

Deployment Details

Courses

All finance courses (UG and MBA); particularly central to Fintech courses

Tools

Multiple AI platforms for cross-platform comparison (ChatGPT, Claude, Gemini, Copilot), custom evaluation rubrics, instructor-designed audit templates

Student Workflow

1. AI Audit exercise: Ask AI a finance question you already know the answer to from class or the textbook. Document the question and AI’s full response.
2. Identify and categorize every error or imprecision: factual, computational, conceptual, reasoning, or omission.
3. Cross-platform comparison: Ask the identical question to ChatGPT, Claude, and Gemini. Document differences in accuracy, depth, and confidence level.
4. Write a 1–2 page ‘AI Reliability Report’ documenting: error types and patterns observed, which platform performed best and worst, specific recommendations for when and how to use AI as a finance professional, and what verification steps you would require before acting on AI output.

Sample Prompts

Explain the Modigliani-Miller theorem. Provide the mathematical proof for Proposition I under the no-tax assumption. Then explain Proposition II and show how the cost of equity changes with leverage. [Student verifies the derivation step-by-step against the textbook, checking for sign errors, missing assumptions, or circular reasoning.]

Using Apple's most recent 10-K filing, calculate the current ratio, debt-to-equity ratio, and return on equity. Show all calculations with the specific line items used. [Student downloads the actual 10-K from SEC EDGAR and verifies every number and calculation independently.]

Ask ChatGPT, Claude, and Gemini: 'What was the S&P 500 total return in 2024? Break down the return into price appreciation and dividend yield.' Compare the three responses for accuracy, specificity, source citation, and confidence level. Which platform hedges most appropriately?

Instructor note: Different AI models have different training data cutoffs. Before this exercise, ask each model "What is your knowledge cutoff date?" and have students record the answer. Discrepancies in S&P 500 return figures may reflect cutoff differences rather than reasoning errors — distinguishing between these two explanations is itself a valuable critical thinking exercise.

Assessment Approach

• Thoroughness of error identification30%
• Accuracy and specificity of error categorization25%
• Quality of actionable recommendations for professional AI use25%
• Depth of cross-platform comparison insights20%

Skills Developed

Evidence

The AAC&U Institute on AI, Pedagogy, and the Curriculum (2024–2026) emphasizes AI literacy as a critical cross-cutting learning outcome. Wharton requires ‘Big Data, Big Responsibilities’ in its AI for Business major. BloombergGPT (Wu et al., 2023) and FinGPT (Yang et al., 2023) provide domain-specific context.

Risks and Safeguards

Lower the barrier to Monte Carlo simulation, option pricing, and scenario analysis dramatically.

Teaching Problem

Finance is fundamentally about decision-making under uncertainty, but building realistic simulations—Monte Carlo portfolio projections, multi-scenario DCF models, option pricing with stochastic volatility, stress tests—traditionally requires significant programming expertise that most finance faculty and students lack.

How AI Addresses the Problem

AI dramatically lowers the barrier to creating sophisticated financial simulations. Faculty or students describe a scenario in natural language—specifying assumptions, distributions, correlations, and output metrics—and AI generates complete, executable simulation code. The pedagogical value is not in the code generation but in what follows: students must set and defend assumptions, modify parameters, interpret distributional outputs, and make recommendations under genuine uncertainty.

Deployment Details

Courses

Investments/Portfolio Management (UG/MBA), Derivatives (UG/MBA), Risk Management (MBA), Financial Modeling (UG/MBA), Capstone courses

Tools

ChatGPT Code Interpreter/Advanced Data Analysis, Claude with code execution, GitHub Copilot, Python (numpy, scipy, pandas, matplotlib), Google Colab

Student Workflow

1. Receive a modeling scenario with specified requirements.
2. Before using AI, write a 1-page specification document: what assumptions about return distributions, correlations, rebalancing frequency, withdrawal rates, and inflation? Justify each choice.
3. Use AI to generate simulation code based on your specification.
4. Run the simulation and produce required visualizations (terminal wealth distributions, probability of ruin, efficient frontier, convergence plots).
5. Modify at least 2 assumptions and re-run: What happens with fat-tailed return distributions? With regime switching? With higher withdrawal rates?
6. Write a 2-page investment recommendation memo supported by simulation evidence.
7. Present findings to the class (5–7 minutes), defending assumptions under Q&A.

Sample Prompts

Build a Monte Carlo retirement simulation in Python with the following specifications: (1) Simulate 10,000 return paths over 30 years for 3 portfolios: 60/40 stocks/bonds, 80/20 stocks/bonds, and a target-date glide path that starts at 90/10 and linearly shifts to 30/70 over 30 years. (2) Use historical Ibbotson-style parameters: stocks with 10.5% mean annual return and 20% standard deviation; bonds with 5.5% mean and 6% standard deviation; correlation of 0.05. (3) Assume $1M starting balance with $50,000 real annual withdrawals (adjusted for 2.5% inflation). (4) Plot: terminal wealth distributions for all 3 portfolios on one chart, probability of ruin (account hitting $0) over time for each portfolio, and the median and 5th/95th percentile wealth paths. (5) Print a summary table showing median terminal wealth, probability of ruin, and the 5th percentile terminal wealth for each portfolio. (6) Set random seed to 42 for reproducibility.

Implement both the Black-Scholes analytical solution and a Monte Carlo option pricing model in Python. Parameters: S0 = $100, K = $105, r = 5%, sigma = 25%, T = 1 year. For Monte Carlo, simulate with N = [100, 500, 1000, 5000, 10000, 50000] paths. Plot: (1) Monte Carlo price vs. number of paths with the Black-Scholes analytical price as a horizontal reference line, (2) 95% confidence interval around the Monte Carlo estimate at each N, (3) computation time vs. number of paths. Explain in comments why the Monte Carlo price converges to the analytical solution and what drives the width of the confidence interval.

Assessment Approach

• Assumption quality and justification25%
• Code modification sophistication20%
• Output interpretation and memo quality25%
• Presentation and defense under Q&A20%
• Verification against analytical solutions10%

Grade-band guidance — Assumption Quality (25%): Full credit requires citing a specific, verifiable data source for each key parameter — e.g., "I used a 10.5% equity mean return based on Ibbotson Associates' long-run historical series, available through Damodaran's data library." Partial credit for reasonable assumptions stated without sources. Minimal credit for assumptions asserted without justification ("I assumed 7% because that seemed reasonable"). The goal is to develop the professional discipline of defending every parameter choice with evidence.

Skills Developed

Evidence

MIT Sloan’s ‘AI and Money’ course (Gensler, 2025) and ‘AI and Machine Learning Applications in Finance’ (Chen, Kogan, Thesmar, 2025) integrate AI-driven modeling. Wharton provides ChatGPT Enterprise to all MBA students (2024). FinGPT (Yang et al., 2023) and PIXIU (Xie et al., 2023) provide open-source frameworks.

Risks and Safeguards