Skip to content
NTPU AI Learn

Learning resources

Public practice files and learning references

Course practice files

Downloadable practice files for AI 101 and the DS courses (DS 101 to DS 302) are collected in the resource browser further down this page, where you can filter by course, preview and download them. Other courses keep their practice material on their own practice pages. For the full task steps, see the practice page for that course.

Learning references

For review after class, the Help Center course catalog lists every published course with its modules and certificate requirements, and each course has its own module pages. The former learner handbook now lives in the Learner Manual.

Help using the platform

Resources are learning assets. For how to use the platform itself (sessions, assessments, progress, troubleshooting), go to the Help Center.

A note on using data

Warning

While practicing, never paste company secrets, customer personal data, or unauthorized sensitive content into any AI tool.

Core Concepts

  • Generative AI: produces new content from your input
  • Agentic AI: plans and executes multi-step tasks
  • Chat / Cowork / Code: three primary work modes
  • Human–AI–Human: a human defines the task, AI executes, a human reviews and stays accountable

Tool Selection

  1. Single-turn, easy-to-state task
    → Chat
  2. Multi-step, multi-source task
    → Cowork
  3. Recurring, well-defined task
    → Code / automation
  4. High-risk, high-impact task
    → Whichever mode, add stronger human review

T-C-R-F Template

  • Task: the concrete, checkable job
  • Context: background, purpose, constraints
  • Reference: source material or examples
  • Format: expected structure, length, tone
Full example

Task: identify the top three issues in this quarter's customer feedback. Context: for the product lead to prioritize. Reference: the attached raw feedback log. Format: three bullet points, each with one line of evidence and one recommendation.

Six-Step Document Analysis

  1. Understand
    What the document is about
  2. Organize
    Break it into issues, owners, timeline
  3. Analyze
    Find patterns, risks, relationships
  4. Question
    Identify information gaps
  5. Produce
    Turn it into a summary or recommendation
  6. Verify
    Check key facts and numbers against the source
  • Useful follow-up: "Which passage supports this conclusion?"
  • Useful follow-up: "Is there any conflicting information?"
  • Useful follow-up: "What here is fact versus your inference?"

Review

  • Fact: explicitly stated in the document
  • Analysis: inference built on facts
  • Unknown: information the document does not provide, needing follow-up
  • AI Review Checklist: can the conclusion be traced back?
  • AI Review Checklist: do the numbers match the source?
  • AI Review Checklist: any unverified inferences?
  • AI Review Checklist: does it match the original task goal?
  1. Can this data leave internal systems?
    Data-safety question 1/4
  2. Does it contain customer PII or confidential material?
    Data-safety question 2/4
  3. Who can see this conversation?
    Data-safety question 3/4
  4. What's the cost of getting it wrong?
    Data-safety question 4/4

Cowork

  • Delegate Task Checklist: is the scope explicit?
  • Delegate Task Checklist: is the delivery format clear?
  • Delegate Task Checklist: is the needed reference material provided?
  • Pre-execution Planning: have AI state its plan first
  • Pre-execution Planning: confirm before it continues
  • Pre-execution Planning: break complex tasks into checkable stages

Code

A one-off task rarely justifies the cost of automation; recurring, well-defined tasks are the ones worth scripting.

Use Case

The Use Case Canvas records: current process, frequency, time spent, pain points, the AI help you want, suggested mode, consequence if wrong, and human-review method.

  • Value check: how often does this happen, and how much time does it cost?
  • Risk check: how serious is the consequence if wrong, and is the data sensitive?

Warning

Do not enter company secrets, customer PII, or unauthorized sensitive content in the Use Case fields.

Post-Class Prompt Cards

Card 1: Executive Summary

Task: turn this document into a one-page summary for a manager. Format: three key points + one recommended action.

Card 2: Meeting Follow-up

Task: list every action item from the meeting notes, with owner and deadline. Format: a table with columns Item / Owner / Deadline.

Card 3: Find the Risks

Task: review this plan and list three possible risks with their triggers. Format: bullets, each with one line of mitigation.

Card 4: Fact/Analysis/Unknown

Task: split this report into fact, analysis, and unknown. Format: three sections, each with bullets.

Card 5: Redesign the Work

Task: analyze this recurring task and suggest which steps suit AI delegation. Format: current steps → suggested change → expected time saved.

Browse by type

Practice files

Filter practice files by course

AI 101 Practice Center

Meeting A: Project Status Meeting

Meeting_A_Project_Status.txt

A single meeting note. Good for Chat, document analysis, Prompt, and Fact / Analysis / Unknown practice.

Download

Meeting B: Cross-Department Follow-up

Meeting_B_Cross_Department_Followup.txt

A cross-department meeting note. Good for multi-document analysis and Cowork delegation.

Download

Sales Report: Sales Data

Sales_Report.csv

CSV sales data. Good for Code / automated analysis and correlation-vs-causation judgment.

Download

Customer Feedback: Raw Excerpts

Customer_Feedback_2026Q3.txt

Raw customer feedback excerpts. Good for classification, evidence citation, sentiment/theme analysis, and Cowork.

Download

DS 101 Practice Center

DS 101 practice data are synthetic educational examples. All company names and values are illustrative and do not represent the ESG performance of any real organization. The metric definitions are simplified for learning and are not a substitute for official ESG accounting or reporting guidance.

Clean ESG dataset

DS101_ESG_Company_Data_Clean.csv

Four illustrative companies, 2020 to 2025, 24 rows. Used in the Guided Lab.

Download

Practice ESG dataset

DS101_ESG_Company_Data_Practice.csv

Practice data with deliberate data-quality problems. Used in the Data Quality Challenge and the Independent Lab.

Download

Data dictionary (Traditional Chinese)

DS101_ESG_Data_Dictionary_zh-TW.csv

Type, unit, requirement and description of every column, in Traditional Chinese.

Download

Data dictionary (English)

DS101_ESG_Data_Dictionary_en.csv

Type, unit, requirement and description of every column; the same fields and units as the Chinese version.

Download

Guided Lab starter notebook

DS101_Guided_Lab_Starter.ipynb

A scaffolded starter notebook with TODO cells; runs top to bottom from a fresh kernel.

Independent Lab starter notebook

DS101_Independent_Lab_Starter.ipynb

A starter notebook with a cleaning decision log and an AI assistance record template.

DS 102 Practice Center

DS 102 practice data is synthetic teaching data. All company names and values are illustrative and do not represent any real organization.

Company master file

DS102_Company_Master.csv

Basic data for 5 synthetic companies: company_id, company_name, sector, hq_region.

Download

Site monthly data (wide format)

DS102_Site_Monthly_Wide.csv

Electricity data for 2 companies, 2 sites each, 12 month columns; used for the reshape and join-cardinality practice.

Download

Company-year clean data

DS102_Company_Year_Clean.csv

5 companies, 2023 to 2025, 15 rows in total. Used for the Guided Lab.

Download

Company-year practice data

DS102_Company_Year_Practice.csv

Practice data with intentional data-quality problems. Used for the Data Quality Challenge and the Independent Lab.

Download

資料字典（繁體中文）

DS102_Data_Dictionary_zh-TW.csv

Column type, unit, required status and description for all three files, in Traditional Chinese.

Download

Data dictionary (English)

DS102_Data_Dictionary_en.csv

English data dictionary; columns and units match the Chinese version.

Download

Guided Lab starter notebook

DS102_Guided_Lab_Starter.ipynb

A starter notebook with guidance and TODOs that runs top to bottom from a fresh kernel.

Independent Lab starter notebook

DS102_Independent_Lab_Starter.ipynb

A starter notebook with a cleaning-decision-log template.

DS 103 Practice Center

DS 103 practice data is synthetic teaching data. All entity names and values are illustrative and do not represent any real organization.

Indicators (clean)

DS103_Indicators_Clean.csv

Clean ESG/campus/operations indicators across several entities and periods: entity_id, period, category, metric, value, unit, denominator, source_note. Used for the Guided Lab.

Download

Indicators (practice, with challenges)

DS103_Indicators_Practice.csv

The same schema with intentional chart-design challenges: a metric with a natural zero baseline, a pair of metrics on very different scales, and a category best shown by shade or pattern alone. Used for the Practice Center and the Independent Lab.

Download

資料字典（繁體中文）

DS103_Data_Dictionary_zh-TW.csv

Column type, unit, grain, allowed values and provenance for the indicators file, in Traditional Chinese.

Download

Data dictionary (English)

DS103_Data_Dictionary_en.csv

English data dictionary; columns and units match the Chinese version.

Download

Guided Lab starter notebook

DS103_Guided_Lab_Starter.ipynb

A starter notebook with guidance and TODOs that runs top to bottom from a fresh kernel, producing three evidence charts.

Independent Lab starter notebook

DS103_Independent_Lab_Starter.ipynb

A starter notebook and checklist template for the Evidence-Based Data Story.

DS 104 Practice Center

DS 104 practice data is synthetic teaching data. All individuals, groups, and values are illustrative and do not represent any real person or organization.

Survey data (clean)

DS104_Survey_Clean.csv

Clean survey/operational-outcomes data across several groups and strata: observation_id, group, outcome, exposure, age_band, sampling_stratum, weight, response_complete. Used for the Guided Lab.

Download

Survey data (practice, with challenges)

DS104_Survey_Practice.csv

The same schema with intentional statistical-judgment challenges: a group whose outcome column is clearly right-skewed with a long tail, a handful of observations flagged for outlier investigation, and a sampling stratum that is clearly under-sampled relative to the stated target population. Used for the Practice Center and the Independent Lab.

Download

資料字典（繁體中文）

DS104_Data_Dictionary_zh-TW.csv

Column type, unit, grain, allowed values and provenance for the survey data file, in Traditional Chinese.

Download

Data dictionary (English)

DS104_Data_Dictionary_en.csv

English data dictionary; columns and units match the Chinese version.

Download

Guided Lab starter notebook

DS104_Guided_Lab_Starter.ipynb

A starter notebook with guidance and TODOs that runs top to bottom from a fresh kernel, producing an EDA profile.

Independent Lab starter notebook

DS104_Independent_Lab_Starter.ipynb

A starter notebook and checklist template for the EDA Report.

DS 105 Practice Center

This is simulated teaching data. All companies, wallets, assets, events and values are fictional and do not represent real companies, investment products or market conditions. Nothing in this course constitutes investment advice.

Simulated on-chain transaction record

DS105_Onchain_Transactions.csv

30-50 simulated transaction rows: timestamp, wallet_id, asset, action, amount, tx_id, with at least 4 wallets, 2 assets, 3 action types, a volume spike, and one ambiguous event that cannot be explained from the data alone. Used in Module 1's AI Evidence Reading Lab and Core Exercise 1.

Download

Simulated financial evidence data

DS105_Financial_Evidence.csv

Revenue growth, debt level, carbon-emissions change, ESG news signal and controversy count for several simulated companies, for practicing multi-source comparison, missing-evidence detection and auditing an overconfident recommendation. Used in Module 2's AI as Evidence Analyst and Core Exercise 2.

Download

Simulated sustainability claims data

DS105_Sustainability_Claims.csv

A set of simulated sustainability claims with matching quantitative indicators (emissions trend, offset share, Scope 3 boundary status, etc.), combined with the transition plan and news extracts into a greenwashing-detection evidence pack. Used in Module 3.

Download

Simulated company transition plan

DS105_Company_Transition_Plan.txt

A simulated company transition-plan narrative with targets, CapEx allocation and timeline, deliberately showing partial transition effort without full Scope 3 coverage. Used in Module 3's greenwashing detection lab.

Download

Simulated external news extracts

DS105_External_News_Extracts.txt

Simulated third-party news and controversy extracts, providing external evidence that may agree or conflict with the company's own claim. Used in Module 3's greenwashing detection lab.

Download

AI Financial Intelligence Canvas template

DS105_AI_Financial_Intelligence_Canvas.md

A field template for the capstone apply exercise (decision, claim, evidence, source fitness, AI analysis, evidence gap, risk, human decision, confidence, rationale), usable as a draft before the online form.

DS 201 Practice Center

The DS 201 practice data is synthetic teaching data; every site, case, and value is illustrative and does not represent any real organization or person.

Service demand data (clean)

DS201_Service_Demand_Clean.csv

A service-demand prediction dataset: case_id, created_at, features_*, target_numeric, target_binary, group_attribute, split_time. Used in the Guided Lab.

Download

Service demand data (practice, with challenges)

DS201_Service_Demand_Practice.csv

The same schema, with deliberate judgment challenges: one column that looks useful but is actually leakage, a baseline scenario that is easy to misuse, and a subgroup with a noticeably higher error pattern. Used in the Practice Center and the Independent Lab.

Download

Data dictionary (Traditional Chinese)

DS201_Data_Dictionary_zh-TW.csv

Column types, units, grain, allowed values, and provenance for the service-demand data file (Traditional Chinese).

Download

Data dictionary (English)

DS201_Data_Dictionary_en.csv

English data dictionary; columns and units match the Chinese version.

Download

Guided Lab starter notebook

DS201_Guided_Lab_Starter.ipynb

A starter notebook with instructions and items to complete, runnable top-to-bottom from a fresh kernel, producing a baseline vs. first-model comparison.

Independent Lab starter notebook

DS201_Independent_Lab_Starter.ipynb

A starter notebook and checklist template for the Predictive Analytics Use Case + Model Card.

DS 202 Practice Center

The DS 202 practice data is synthetic teaching data; every service group, record, and value is illustrative and does not represent any real organization or person.

Analysis package (clean)

DS202_Analysis_Package_Clean.csv

A service analysis dataset: record_id, period, group, value, unit, status, sensitive_flag, source_version. Used in the Guided Lab.

Download

Analysis package (practice, with challenges)

DS202_Analysis_Package_Practice.csv

The same schema, with deliberate judgment challenges: a column that looks useful but is actually hallucinated (not part of the canonical schema), analysis flaws from not filtering by status, a duplicated record_id, and at least one row where sensitive_flag is true. Used in the Practice Center and the Independent Lab.

Download

Data dictionary (Traditional Chinese)

DS202_Data_Dictionary_zh-TW.csv

Column types, units, grain, allowed values, and provenance for the analysis package file (Traditional Chinese).

Download

Data dictionary (English)

DS202_Data_Dictionary_en.csv

English data dictionary; columns and units match the Chinese version.

Download

Guided Lab starter notebook

DS202_Guided_Lab_Starter.ipynb

A starter notebook with instructions and items to complete, runnable top-to-bottom from a fresh kernel, practicing context-setting, verifiable prompts, and read-before-run.

Independent Lab starter notebook

DS202_Independent_Lab_Starter.ipynb

A starter notebook and checklist template for the AI-Assisted Workflow + Verification Record.

DS 301 Practice Center

DS 301 practice data is synthetic teaching data. Every source system, batch, and value is illustrative and does not represent any real organization or individual.

Monthly analytics package (clean)

DS301_Analytics_Package_Clean.csv

A monthly analytics dataset: run_id, source_system, batch_id, event_time, ingested_at, entity_id, metric, value, schema_version. Used for the Guided Lab.

Download

Monthly analytics package (practice, with challenges)

DS301_Analytics_Package_Practice.csv

Same field structure, with deliberately designed challenges: late-arriving events, one schema change, a duplicated batch_id, and at least one row that violates the contract. Used for the Practice Center and the Independent Lab.

Download

Data dictionary (Traditional Chinese)

DS301_Data_Dictionary_zh-TW.csv

Field types, units, grain, allowed values, and provenance for the analytics package (Traditional Chinese).

Download

Data dictionary (English)

DS301_Data_Dictionary_en.csv

English data dictionary; fields and definitions match the Chinese version.

Download

Guided Lab starter notebook (notebook → pipeline refactor)

DS301_Guided_Lab_Starter.ipynb

A starter notebook with guidance and tasks to complete, practicing splitting exploratory code into ingest/validate/transform/analyze/publish stages.

Independent Lab starter notebook / template

DS301_Independent_Lab_Starter.ipynb

Starter notebook and checklist template for the Analytics Workflow Canvas + Executable Workflow Prototype + Runbook.

DS 302 Practice Center

DS 302 practice data is synthetic teaching data. Every source system, batch, and value is illustrative and does not represent any real organization or individual.

Governed analytics sandbox (clean)

DS302_Analytics_Package_Clean.csv

A read-only query log against the governed analytics sandbox: run_id, source_system, batch_id, event_time, ingested_at, entity_id, metric, value, schema_version. Used for the Guided Lab.

Download

Governed analytics sandbox (practice, with challenges)

DS302_Analytics_Package_Practice.csv

Same field structure, with deliberately designed challenges: late-arriving events, one schema-drift value, a duplicated run, and at least one row that violates the data contract. Used for the Practice Center and the Independent Lab.

Download

Data dictionary (Traditional Chinese)

DS302_Data_Dictionary_zh-TW.csv

Field types, units, grain, allowed values, and provenance for the analytics sandbox (Traditional Chinese).

Download

Data dictionary (English)

DS302_Data_Dictionary_en.csv

English data dictionary; fields and definitions match the Chinese version.

Download

Guided Lab starter notebook (verifiable read-only agent)

DS302_Guided_Lab_Starter.ipynb

A starter notebook with guidance and tasks to complete, practicing plan → read-only query → dataset-version citation → verification.

Independent Lab starter notebook / template

DS302_Independent_Lab_Starter.ipynb

Starter notebook and checklist template for the Data Agent Architecture Canvas + Governed Prototype + Evaluation Pack.

Reference materials

Full course catalog

Reference material for every published course is kept in the Help Center course catalog, updated as new courses go live.

Go to course catalog

What next?