Course 2026-2027 a.y.

The course is organised around four connected macro-topics, each building directly toward the intended learning outcomes.

1. Foundations of AI-assisted work. What current AI assistants can and cannot do; setting up an AI working environment; the Read–Think–Act workflow for delegating real tasks; prompt engineering fundamentals (specificity, output-format control, iterative refinement); project-level configuration through structured instructions and reusable prompt libraries. (Supports: workflow design; prompt refinement.)

2. Data analysis and visualisation with platform data. Reading, inspecting, and cleaning real-world datasets (missing values, duplicates, formatting); aggregation and comparison across groups and over time; principles of chart design, storytelling, and dashboards; sentiment analysis and theme extraction from user-generated text; structured web research and fact-checking; experiment design, bias audits, and the distinction between correlation and causation. (Supports: quantitative and qualitative analysis; visualisation and report generation; critical evaluation of accuracy and bias.)

3. Computational social science applications. Digital platform economics (network effects, multi-sided markets, market concentration); AI and the future of work, including task-level automation exposure and labour-market implications; analysis of online discourse (sentiment, frames, stance, temporal dynamics); an integrative case study combining data, stakeholder context, and policy synthesis into a professional brief. (Supports: end-to-end analysis from problem formulation to actionable recommendations; translating results into strategic decisions.)

4. Advanced workflows and the professional toolkit. Designing reusable analytical capabilities (custom Skills); building automated research pipelines that combine multiple tools and data sources; coordinating parallel AI workflows on a single research question; study design, ethics, validation habits, AI disclosure, and assembling a personal toolkit for AI-augmented work that students can carry into internships and full-time roles. (Supports: workflow automation; professional communication; responsible AI use.)

Each macro-topic is delivered through short lectures, structured hands-on exercises, and a semester-long group project in which students apply the full workflow — from problem formulation through analysis, validation, and presentation — to a topic of their choice.

At the end of the course, students will be able to:

- Describe how modern AI assistants work, what they reliably do well, and where they fail (hallucination, absence of real-time data, limits of causal reasoning).
- Identify the components of an effective prompt and the principles of iterative refinement.
- Recognise the main classes of analytical tasks AI tools can support: data cleaning, aggregation, visualisation, text analysis, web research, and workflow automation.
- Explain how reusable AI capabilities — custom Skills, automated pipelines, multi-agent workflows — are structured and when each is appropriate.
- Outline the ethical, validation, and disclosure obligations that govern professional AI use.

At the end of the course, students will be able to:

- Clean, analyse, and visualise real quantitative and qualitative datasets with the support of AI tools.
- Conduct structured web research and fact-check AI-generated claims against primary sources.
- Critically evaluate AI outputs for accuracy, bias, and reliability, and refine prompts to improve performance.
- Build reusable analytical assets — custom Skills and automated pipelines — that scale individual productivity.

- Design AI-assisted workflows that take a business question from problem formulation to actionable recommendation.

• Lectures
• Individual works / Assignments
• Collaborative Works / Assignments

☑ Face-to-face lectures
Each of the 18 content sessions opens with a lecture part introducing the concept, the relevant AI capability, and the business motivation, and closes with a synthesis recapping key takeaways and common pitfalls.

☑ Practical exercises / Lab work
The core of each content session is a hands-on exercise in which students use Claude Code on their own laptops to complete a realistic analytical task (cleaning a dataset, building a dashboard, drafting a policy brief, etc.). Exercises follow a progressive structure: guided, semi-guided, independent.

☑ Group assignments / Project work
A semester-long group project runs in parallel to the lectures, with dedicated project sessions for kickoff, mid-point checkpoint, and final presentations. Groups choose their own research question and deliver a final analysis and presentation.

• Participation: 30%

  • Engagement in class, completion of in-class exercises.

• Assignments and Project: 30%

  • A set of individual or group assignments throughout the course.

• Final Exam: 40%

  • Written exam on both conceptual knowledge and applied skills developed in the course.

(Students need to more than 75% all sessions in person to be qualifed as attending students)

• Assignments and Project: 50% 

Final individual project

• Final Exam: 50%

Written exam covering both conceptual knowledge and applied skills developed in the course.

• Lecture slides and Jupyter notebooks prepared by the instructor.

• Selected academic papers, reports, and practitioner articles on AI and market research.

• Links and documentation for LLM / AI tools and APIs used in class.