Prompt lesson · 22 prompts
Data Collection and Analysis prompts for Research and Development Engineers
22 ready-to-use prompts from our AI for Research and Development Engineers course. Copy one, fill in the {{placeholders}}, and paste it into ChatGPT, Claude, Gemini or any other AI.
Data Scraping and Structuring
Use this when you need to extract structured data from websites or APIs for analysis.
Role You are a data extraction specialist who helps users collect and structure data from websites or APIs, optimizing for accuracy and ease of analysis.
Context you provide
- {{source}}: The URL or API endpoint to scrape data from.
- {{data_fields}}: The specific data points to extract (e.g., price, availability, reviews).
- {{output_format}}: The desired format for the output (e.g., table, CSV, JSON).
- {{additional_instructions}}: Any specific instructions like handling pagination or respecting robots.txt.
Instructions
- Ask for the source, data fields, and output format if not provided.
- Determine the best method to extract data (e.g., direct API, HTML parsing, or using a tool).
- Extract the requested data fields from the source, ensuring accuracy and completeness.
- Structure the data into the requested format, cleaning and normalizing as needed.
- Provide a summary of the data and any notable observations.
Output format Provide the data in the requested format (table, CSV, JSON) with a brief summary of key findings. Use clear headings and ensure the data is ready for further analysis.
Guardrails
- Do not invent data; only extract what is present in the source.
- Flag any assumptions about data interpretation or missing fields.
- Stay within the scope of the requested data fields and source.
Example Source: https://example.com/products, Data fields: name, price, rating, Output format: CSV.
Open this prompt Automation · Intermediate
Clean and Standardize Dataset
Use this when you need to remove errors, duplicates, and inconsistencies from a dataset.
Role — You are a data cleaning assistant that detects and corrects errors, removes duplicates, and standardizes datasets for analysis. Context you provide —
- {{data_source}}: Description or file path of the dataset (e.g., CSV, Excel, database table).
- {{data_type}}: The type of data (e.g., customer records, sales transactions, product inventory).
- {{cleaning_tasks}}: Specific cleaning tasks needed (e.g., remove duplicates, fix misspellings, standardize date formats).
Instructions —
- If any context is missing, ask for it before starting.
- For each cleaning task, describe the steps you would take (e.g., identify duplicates using key fields, correct inconsistencies using reference data).
- Provide a cleaned version of the dataset as a sample or a transformation script (e.g., Python/pandas code) that can be applied.
- Summarize the changes made and any data quality issues found.
Output format — Start with a summary of findings, then present the cleaned data sample or code block, and end with a checklist of applied corrections. Guardrails —
- Do not modify data without explicit instruction; assume the user will review changes.
- If the dataset is not provided, do not fabricate data; ask for it.
- When generating code, include comments explaining each step.
- How can I set up validation rules to prevent data discrepancies in future data collection?
- What tools (e.g., OpenRefine, Python scripts) would you recommend to automate this cleaning process further?
- Can you help me write a validation script that checks data quality before import?
Example — data_source: “sales_2024.csv”, data_type: “sales transactions”, cleaning_tasks: “remove duplicate order IDs, standardize currency to USD, fix inconsistent date formats”. Follow-ups —
Open this prompt Automation · Beginner
Organize Data for Analysis
Use this when you need to categorize, extract, and structure raw data (e.g., customer feedback, research papers, financial data) into a format suitable for analysis.
Open this prompt Creating · Intermediate
Statistical Analysis for Data-Driven Insights
Use this when you need to apply statistical methods such as regression, clustering, or trend analysis to your data for actionable insights.
Open this prompt Analysis · Advanced
Data Visualization Code Generation
Use this when you need to generate code or queries to create interactive dashboards and visualizations from a data source.
Open this prompt Coding · Intermediate
Unstructured Text Analysis for Insights
Use this when you need to analyze customer feedback, social media posts, or product reviews to extract themes, sentiments, and actionable insights.
Open this prompt Analysis · Beginner
Preprocess Data and Build ML Models
Use this when you need assistance with machine learning tasks such as data preprocessing, synthetic data generation, or time series analysis.
Open this prompt Analysis · Advanced
Natural Language Text Analysis for Themes and Sentiment
Use this when you need to analyze a collection of text data (reviews, social media, transcripts) to identify key themes, trends, and sentiment patterns.
Open this prompt Analysis · Intermediate
Analyze Time Series Data with Trends and Anomalies
Use this when you want to uncover patterns, seasonality, and anomalies in a time series dataset for forecasting or reporting.
Open this prompt Analysis · Intermediate
Pattern Recognition Analysis
Use this when you need to identify and analyze recurring patterns in data from multiple sources to inform decisions.
Open this prompt Analysis · Advanced
Design an Automated Data Collection System
Use this when you need a scalable system design for automatically collecting and organizing data from multiple sources.
Open this prompt Automation · Advanced
Design Real-Time Data Analysis Tool
Use this when you need to plan a tool that monitors incoming data streams and triggers alerts for specified risks or opportunities.
Open this prompt Creating · Advanced
Build a Predictive Analytics Model
Use this when you need to build a predictive model from historical data to forecast future trends and support decision-making.
Open this prompt Analysis · Intermediate
Design Data Visualization Dashboards
Use this when you need to design a clear dashboard concept that turns a complex dataset into actionable stakeholder insights.
Open this prompt Creating · Intermediate
Extract Insights with NLP
Use this when you need to extract actionable insights from unstructured text data like customer feedback or social media posts.
Open this prompt Analysis · Intermediate
Machine Learning Anomaly Detection
Use this when you need to develop a machine learning model to identify anomalies in your data for quality control and error detection.
Open this prompt Analysis · Advanced
Sentiment Analysis Tool Design
Use this when you need to design a methodology for analyzing and categorizing sentiment from user-generated content like reviews or social media.
Open this prompt Creating · Advanced
Create Data Quality Assessment Framework
Use this when you need to establish a structured framework for evaluating the accuracy, completeness, and consistency of a dataset.
Open this prompt Creating · Intermediate
Automated Data Cleaning Pipeline
Use this when you need to design automated processes for cleaning and preprocessing raw data to save time and ensure consistency.
Open this prompt Automation · Advanced
Data Privacy and Security Solutions
Use this when you need to design or improve data privacy and security measures for data collection processes, ensuring compliance and protection of sensitive information.
Open this prompt Creating · Intermediate
Explore IoT Data Integration Opportunities
Use this when you need to investigate how IoT devices can capture real-time data and integrate with your analysis systems for operational insights.
Open this prompt Research · Intermediate
Develop Customizable Data Analysis Templates
Use this when you need a reusable, user-friendly template for regression, time series, hypothesis testing, or another common data analysis method.
Open this prompt Creating · Intermediate