Using Data Conversations

Using Data Conversations#

Note

Data Conversations is currently in BETA and available to selected customers only. We’ll be expanding its capabilities based on user feedback while maintaining the core interface and functionality.

This guide explains how to use Data Conversations, Adverity’s natural language interface for exploring your data.

Introduction#

Data Conversations reshape how you interact with your data by allowing you to simply ask questions and receive immediate insights. This feature enables anyone in your organization to access data insights without technical expertise or SQL knowledge.

Whether you need quick answers about campaign performance, want to identify trends, or need to share insights with stakeholders, Data Conversations makes your data truly accessible and actionable.

Note

Data Conversations uses large language models (LLMs) to power its conversational AI capabilities. Adverity leverages OpenAI technology for processing natural language requests. Only column names and necessary database metadata are sent to OpenAI to generate SQL queries, which are then executed within Adverity’s secure environment. Your actual data remains within Adverity, and no personal data is shared with external providers.

Benefits of Data Conversations#

  • Get immediate answers about your data without writing SQL queries.

  • Empower team members of all technical levels to explore data independently.

  • Reduce time spent on repetitive data queries and report creation.

  • Access the information you need when you need it for better decision making.

  • Easily share data insights with colleagues and clients.

Prerequisites#

This feature is available only to users with Conversations manager permissions. For more information, see Managing user permissions.

Accessing Data Conversations#

  1. Go to the Data Conversations page.

  2. Begin typing your question or select one of the suggested queries.

Asking effective questions#

The key to getting the most out of Data Conversations is asking clear, specific questions. Consider including the following in your request:

  • Field names (e.g., “Revenue”, “Clicks”, “Impressions”)

  • Time periods (e.g., “last month”, “Q1 2025”, “year-to-date”)

  • Metrics (e.g., “CTR”, “conversion rate”, “ROI”)

Try questions like:

  • What were our top 5 campaigns by Revenue last month?

  • Show me CTR by device type for our Facebook campaigns in Q1.

  • Compare conversion rates across channels for the past 30 days.

  • What’s the trend in Cost per Acquisition for our Google Ads campaigns this year?

Tips for getting the best results#

  • Start broad, then narrow down: Begin with a general question and use follow-ups to focus on specific details.

  • Use date ranges: Specify time periods to get more relevant results (e.g., “this month”, “last quarter”, “year-to-date”).

  • Compare metrics: Ask about relationships between different data points (e.g., “How does CTR correlate with conversion rate across our campaigns?”).

  • Explore different angles: Look at your data from various perspectives (e.g., by channel, by audience segment, by geographic region).

  • Use context: Data Conversations remembers previous questions, so you can ask follow-ups without repeating all details.

Common question types#

Performance summaries

“Summarize our campaign performance for Q1 2025.”

Trend analysis

“Show the trend of our website traffic over the past 6 months.”

Comparisons

“Compare the ROI of our email campaigns versus social media campaigns.”

Top performers

“What are our top 10 keywords by conversion rate?”

Audience insights

“Which customer segments have the highest lifetime value?”

Working with responses#

After asking a question, you get an answer that may include:

  • Text explanations of the data

  • Data tables with relevant information

  • Visualizations (bar or line charts)

Follow-up suggestions#

After getting a response, you’ll see suggested follow-up questions. Use these to dig deeper into your data or explore related aspects.

Viewing SQL#

Click View SQL under any response to see the query used to retrieve your data. This can help you understand the specific data used in the insights.

Downloading results#

For data tables

Click Download data to export the insights as a CSV file.

For charts and visualizations

Click Download image to save the insights as an image file.

Sharing and using insights#

Once you got the insights you need, share them with your colleagues:

  • Save important conversations for future reference.

  • Export data and visualizations for presentations or further analysis.

  • Share insights directly with team members in Adverity.

  • Use findings to inform campaign optimizations and strategy decisions.

When to use Data Conversations?#

Data Conversations can help you understand your data better and faster:

  • Experiment with different question types to explore your data.

  • Use Data Conversations for quick answers during meetings or strategy sessions.

  • Incorporate insights into your regular reporting and analysis workflow.

  • Provide feedback on responses to help improve the system’s accuracy and relevance.

As you use Data Conversations more, you’ll develop a deeper understanding of your data and uncover valuable insights. Don’t hesitate to experiment with different questions – the system is designed to help you explore and learn.

Contents