Using the AI Analyst ✨

Introducing the AI Analyst 3.0 ✨

The AI Analyst 3.0 is biggest AI release in 15 months. It lets you run more sophisticated analyses and perform data operations using only natural language. Let's go through its main features.

The new AI Analyst 3.0 comes equipped with several key features:

• 💬 Conversational UX: A chat interface, just like you're used to in ChatGPT. Ask your questions or requests, and the AI Analyst will process and respond accordingly.
• ✈️ New capabilities: The new Analyst is as a true spreadsheet assistant, and it comes with 6 different capabilities including data analysis, adding columns, creating charts, enriching data and formatting cells.
• 🧠 Smarter model: The Analyst is powered by the latest OpenAI's gpt-4o model, which offers a nuanced understanding of queries and delivers accurate, context-aware responses.

Preparing Your Data for the AI Analyst

To ensure optimal performance of the AI Analyst:

• Ensure your table has clear, unique headers in the first row.
• Include at least one full row of data below the headers.
• For tables with date/time headers (e.g., P&L reports), the AI will assume a vertical orientation and treat the first column as headers.

How to use the AI Analyst

Using the AI Analyst is straightforward:

1. Find the sparkle ✨ icon in the top right corner of any table.

2. Click to open the AI Analyst panel on the right side of your screen.

3. Begin your interaction by typing your questions or requests.

The AI Analyst 3.0 is versatile in its data handling and copilot capabilities. To make the most of the AI Analyst, it's worth understanding its thought process and how it handles your question.

How the AI Analyst thinks

Three main principles to keep in mind when asking questions to the Analyst:

1. Context: The Analyst derives its knowledge about the dataset from a sample of rows and the header. This means it's able to understand and infer operations based on the context. For example, if your table has cost and revenue columns, you can ask it to compute profit.

2. Single operation: The Analyst can perform one operation at a time. This means that inquiries involving multi-step operations need to be broken down and asked one by one. For example, if you have a column with dates and another with the number of website visitors, and you want to create a table with weekly traffic, you need to first ask to add a column with the respective year-week and then create a table with the aggregation.

3. Single-table analysis: The Analyst only analyzes data from one specific table at a time. This means that even when your question generates a new table, your subsequent queries will still refer to the original table. If you want to create a Chart of this new table, you'll need to select the AI Analyst of that table and ask it there.

With these principles in mind, let's explore the main capabilities of the AI Analyst 3.0.

Key Analyst capabilities

1. Data Analysis

The AI Analyst 3.0 efficiently processes numerical data for metrics, data slicing, and table transformations.

Examples of questions:

• "What is our top-selling product in each region?"
• "Provide a breakdown of our customer base by age group and average purchase value."
• "What's the median salary for females?"

✏️ Tip: Refer to the column name you want to execute the action on. Mention explicitly the aggregation operation you want to perform or the dimension you want to use to pivot/slice the original dataset.

⚠️ Warning: If you need to perform an operation that requires different intermediate steps, ask it one at a time. For example: on a daily sales dataset, to analyze weekly data, you need to first add a week column, and then aggregate the key metrics.

✅ Effective Query: "What is the average and median revenue for each product category?"

❌ Less Effective Query: "Tell me insights about our sales."

2. Add a Column

The AI Analyst 3.0 can create new columns and understand your table's context based on column titles and sample data.

For instance, with "Revenue" and "Cost" columns, you can simply request to add a "Profit" column. The AI Analyst can also enrich your table with AI-powered functions, performing actions like sentiment analysis, data mining, or classification tasks.

See the example below, where the address column is categorized into broader regions:

In the following video, instead, the dataset is enriched with the real-time stock price:

Examples of questions:

• "Calculate the profit margin for each sale."
• "Extract the numerical portion of the user_id."
• "Add a column with current stock prices for each company in our portfolio."

✏️ Tip: To avoid misunderstanding, be clear about the logic you want to include in the column.

✅ Effective Query: "Add a 'Sentiment' column for each customer review"

❌ Less Effective Query: "Make a new column with sentiment analysis."

See below the full list of transformations supported in columns:

3. Add Chart

The AI Analyst 3.0 can create charts to visualize your data effectively.

Examples of questions:

• Bar Chart: "Create a bar chart showing total sales by product category."
• Column Chart: "Generate a column chart of monthly website visitors over the past year."
• Combo Chart: "Create a combo chart with a column chart of revenue and a line chart of profit margin on the secondary axis."

✏️ Tip: Specify your preferred chart type, and what you want to see on both axes.

✅ Effective Query: "Create a stacked area chart showing market share trends for our products."

❌ Less Effective Query: "Make a chart of the numbers."

4. Format ranges of cells

The AI Analyst 3.0 can apply various formatting styles to ranges of cells, to enhance readability and highlight key information.

Examples of questions:

• "Format the 'Total Revenue' column as USD."
• "Format the header in bold, red background."
• "Format range A1:B10 in light blue'

Formatting Options:

• Font styles: Bold, Italic, Underline
• Colors: Font color, Background color
• Number formats: Currency, Percentage, Date/Time
• Text alignment: Left, Center, Right

✏️ Tip: Always mention the data range you want to format and the rule to apply.

✅ Effective Query: "Format the 'Growth Rate' column as percentage."

❌ Less Effective Query: "Make the spreadsheet look nice."

5. Other Dataset-Related Questions

The AI Analyst can handle a wide range of queries about your data, offering a variety of insights.

Examples of questions:

• "What can I ask you to do?"
• "What does the column 'Bayesian classifier' mean"?
• "How does our product performance vary across different regions and seasons?"

✏️ Tip: Consider asking questions whose answers can clearly be surfaced using the available data. Avoid asking for insights out of the scope of the dataset.

✅ Effective Query: "Based on the salary data, is it worth pursuing an MBA?"

❌ Less Effective Query: "What's in this spreadsheet?"

Future Developments

We're continually working to enhance the AI Analyst 3.0. Here's a preview of what's coming next:

• Multi-step operations: The Analyst will solve multi-step operations in a single prompt.
• Multi-table context: The AI Analyst will be aware of other tables in your spreadsheet, and able to perform actions across different tables in your spreadsheet, e.g. perform a VLOOKUP across two datasets.
• New capabilities: The new versions will support new operations such as finding & replacing text, applying Conditional Formatting, removing columns or create datasets and models for advanced analytics.

Data Privacy

We prioritize the security of your data:

• Your data is not used to train models that could benefit other users.
• We transmit only the minimum necessary information to the AI algorithm.
• For comprehensive information about our data handling practices, please visit rows.com/privacy.

We're committed to continuously improving the AI Analyst's capabilities. Stay tuned for updates in the coming weeks and months.

Frequently Asked Questions

How do I activate AI Analyst in Rows?

The AI Analyst is accessible to all users. Look for the ✨ icon next to the filter and settings options of any table.

What are the usage limits for AI Analyst?

The Free plan includes 30 queries per month. The Plus plan offers unlimited usage.

Which model powers the AI Analyst?

The AI Analyst uses OpenAI's GPT-4o model. We regularly update it to the latest available models.

Can I use a different model with the AI Analyst?

Currently, we exclusively use OpenAI's GPT-4o model. For enterprise solutions or custom requirements, please contact us at enterprise@rows.com or use the "Chat with us" option in your Rows account's support menu.

Is my data used for model training?

No. The AI Analyst does not use your data to train models that could be used by others. We minimize the data sent to the AI algorithm. For more details on our data processing, visit rows.com/privacy.

Does OpenAI use the data they receive for training?

No. OpenAI does not use customer-submitted data via their API for model training or improvement without explicit opt-in. Refer to OpenAI's consumer privacy FAQs for more information.

What data is shared with the model?

To protect your privacy, we send OpenAI a summary of your dataset, including:

• Table headers
• A sample of up to 5 rows of data
• Basic dataset statistics (e.g., min and max values)

Personal data is only shared if it's included in the first row/column or the sample rows. We do not send complete tables to OpenAI.

Is there a limit to the amount of data the AI Analyst can process?

There are no set limits. We send only a summary of your dataset to OpenAI's APIs, allowing the AI Analyst to process datasets of any size within Rows.

What should I do if the AI Analyst is taking longer than expected?

If processing time exceeds 30 seconds, we recommend waiting briefly and trying again.

How can I suggest new features?

We welcome your feedback and feature requests. You can submit them on our public board at feedback.rows.com or via the in-app chat (access via the question mark (?) in the top-right corner > Help > Chat with us).

Additional Resources

To further enhance your AI-powered data analysis skills, consider exploring these tutorials:

• Enhancing SEO with OpenAI
• Efficient Content Redaction
• Advanced Data Extraction Techniques
• Optimizing Keyword Research
• Customer Feedback Classification
• Implementing Sentiment Analysis
• Streamlining Data Cleanup