Skip to content
NTPU AI Learn
DS 202AdvancedL1 + L2 Certificates

AI-Assisted Data Science

Use generative AI as an accelerating but verifiable data-science collaborator: understand what AI can and cannot do, provide schema and context, write verifiable prompts, review AI-generated Python before running it, pair with AI in a Guided Lab, debug both runtime and silent analytical errors, verify in layers (data, code, method, claim), record prompt logs and provenance, decide whether sensitive data may reach an AI service, and deliver an auditable AI-assisted workflow in the Independent Lab, completing an AI-Assisted Data Science Workflow + Verification Record.

7 hours2 modules中文 / EnglishLast verified

The course storyline: from a question to auditable evidence

The whole course follows one line: Human Question, AI Proposal, Executable Analysis, Verification, Revision, Evidence. AI may help propose and write code; people stay responsible for verification and the final judgment.

  1. 1. Human Question

    What is the analysis question, and what decision does it support?

  2. 2. AI Proposal

    Given the data context you supplied, what method did AI propose?

  3. 3. Executable Analysis

    Was the code checked item by item before running (read before run)?

  4. 4. Verification

    Was it verified across the Data, Code, Method, and Claim layers?

  5. 5. Revision

    Once a gap or silent error was found, was it fixed and re-verified?

  6. 6. Evidence

    Does the final claim faithfully reflect the evidence, with a provenance record attached?

Your next step

DS 202 · Module 1: AI-Assisted Analysis: From Question to Executable Code

0 / 18 items done0%
Start learning

Curriculum

  1. Module 1AI-Assisted Analysis: From Question to Executable CodeStart with what AI can and cannot do, then learn to provide data context, write verifiable prompts, and review AI-generated Python before running it, before pairing with AI on a first verifiable analysis in a Guided Lab.Not started0 / 5 · about 210 min
  2. Module 2Trustworthy AI Data Science: Verification, Reproducibility, and GovernanceLearn to separate runtime errors from silent analytical errors, verify in layers with the Verification Ladder, record prompt logs and provenance, and decide on AI governance for sensitive data, then deliver an auditable AI-assisted workflow in an Independent Lab.Not started0 / 5 · about 210 min

Progress is stored in this browser and does not identify you. It is uploaded only if you join progress sync below.

Sync my progressJoin a session to keep progress across devices and share it with your instructor

Info

After you join, your completed lesson numbers are sent to your instructor together with your learner code, so they can see your progress. Use the codes your instructor gave you, and do not enter your name, company secrets or other personal data. Progress is kept with the rest of that session's data.

Save as PDF

Practice and assessment

About this course

Outcomes

  • Map AI roles across framing, code, debugging, interpretation, documentation; retain human responsibility
  • Provide schema, grain, units, allowed operations, and forbidden assumptions
  • Write task/context/requirements/output/verification prompts for data analysis
  • Review imports, columns, filters, joins, formulas, side effects, and expected outputs before execution
  • Use AI to propose and implement an analysis, then independently verify each critical step
  • Complete the final artifact: AI-Assisted Data Science Workflow + Verification Record

Certificate

Earns a course completion certificate (L1); a capability certificate (L2) is also available through additional artifact review.

Requirements to earn it

  • Complete all 2 course modules
  • Pass the post-test assessment at 80% or higher
  • Submit a project artifact and pass review

Course feedback

It takes 2 to 3 minutes and is used to improve the course.

Give feedback