Empowering business users to become data storytellers with Amazon Q in QuickSight
- Categories
- Date
- Author
- Data & Visualisation, Data & Analytics, Generative AI
- April 15, 2024
- Ahmed Nuaman
Businesses are becoming more reliant on data than ever before, which means the ability to extract meaningful insights from vast amounts of information, and effectively communicate them has become a critical skill. However, not all business users are equipped with the technical expertise to navigate complex data systems and create compelling data visualisations. This is where Amazon Q, the generative AI-powered assistant, in Amazon QuickSight, steps in to empower users to become data storytellers, and unlock the full potential of their organisation’s data.
This article explores how Amazon Q empowers business users to confidently understand data better, and create compelling data visualisations and narratives, using the capabilities of Generative BI.
Overcoming the limitations of traditional BI tools
Traditional business intelligence (BI) tools typically require technical expertise for effective navigation, restricting non-technical users from actively engaging with data and discovering valuable insights. In addition, these conventional BI workflows often involve a lengthy process of data preparation, dashboard creation, and report generation, which can be time-consuming and frustrating for business users.
Introducing Amazon Q, seamlessly integrated with Amazon QuickSight, has been a game-changer for organisations, and effectively bridges the gap posed by these challenges. It provides a user-friendly, natural language-based interface that empowers a wider audience to explore data.
This capability not only saves time but also allows business users to explore data on their own, reducing their reliance on IT or BI teams. Instead of waiting for these teams to update dashboards or generate reports, users can self-serve and uncover insights that may have been previously overlooked, providing agile responses to changing business conditions.
With Amazon Q, business users can now:
Ask natural language questions
Using natural language processing (NLP), QuickSight Q enables users to ask questions about their data in everyday language, eliminating the need for data modelling or SQL querying knowledge.
Generate insightful visualisations
In real-time, the system analyses queries, understands context, retrieves data from relevant sources, and can generate custom charts, graphs, and dashboards based on the users’ queries. The flexibility to customise visualisations and dashboards ensures that users can tailor the QuickSight experience to their specific business needs and preferences, allowing them to present data in a clear and compelling way.
Summarise key findings and narratives
Amazon Q goes beyond only providing data visualisations, but also allows users to become data storytellers, by creating compelling narratives that bring the data to life. With the ability to generate executive summaries, identify emerging trends, and make data-driven recommendations, users can effectively communicate their findings to stakeholders, allowing for faster, more informed decision making without having to sift through vast amounts of data themselves.
Collaborate and share insights
With over 40 built-in connectors, Amazon Q seamlessly integrates with existing collaboration tools, such as Slack, Salesforce and Microsoft Teams, allowing business users to share their data-driven insights and findings with their colleagues in real-time.
Technical architecture of Amazon Q in QuickSight
Amazon Q’s integration with QuickSight is built to offer an intuitive, scalable, and highly efficient analytics platform. The architecture combines advanced natural language processing (NLP), serverless data processing, and visualisation components, ensuring a streamlined end-to-end solution for business intelligence.
Key Components of the architecture
1. Data Ingestion and Storage:
AWS Cost and Usage Reports (CUR): The architecture starts with granular data ingestion via AWS CUR, stored in Amazon S3.
ETL with AWS Glue: Data preparation and transformation tasks leverage AWS Glue to structure the CUR for querying.
2. Querying and Processing:
Amazon Athena: CUR data is queried using Amazon Athena, a serverless, SQL-based query engine for scalable and efficient data retrieval.
Amazon QuickSight Engine: Integrated with Amazon Athena, QuickSight processes data to generate real-time insights.
3. Amazon Q for NLP Queries:
Natural Language Processing: Amazon Q translates plain-text business queries into structured data queries.
Integration: Through seamless integration, Q allows business users to interact with data dynamically without technical expertise.
4. Visualisation and Insights:
Dynamic Dashboards: Amazon QuickSight generates interactive dashboards, reports, and visual narratives.
Tagging and Contextual Insights: Amazon Q integrates tagging strategies and connects to the CUDOS Dashboard to provide enriched, account-specific insights.
Architecture Workflow
AWS CUR (Cost and Usage Report): The architecture starts with detailed cost and usage data ingested and stored in Amazon S3.
Amazon Glue ETL: CUR data undergoes transformation and structuring.
Athena Query Layer: Transformed data is queried for specific insights.
Amazon Q Integration: Allows business users to input natural language queries that are interpreted into analytical insights.
QuickSight Visualisation: Outputs real-time dashboards, charts, and narratives tailored to business needs.
Driving innovation across industries
The Amazon Q feature within the QuickSight platform has empowered business users across diverse industries to become effective data storytellers, driving innovation, improving operational efficiency, and gaining a competitive edge.
One example of a successful case study demonstrating innovation in the financial services industry is Nasdaq, the world’s second-largest stock exchange. Prior to implementing Amazon Q, Nasdaq faced several key challenges in leveraging its data effectively. The company’s trading data was highly complex and not well-suited for analytics, as the systems were designed for speed rather than analysis. Furthermore, Nasdaq’s business users were becoming increasingly frustrated with the difficulty in obtaining the data insights they needed, as different teams had developed their own siloed approaches to data analysis, hindering collaboration and the sharing of insights.
By implementing Amazon Q in QuickSight, Nasdaq was able to empower its business users to become collaborative data storytellers and make more informed decisions. The natural language interface of Amazon Q allowed Nasdaq’s non-technical employees to easily explore data and generate custom visualisations together, without the need for specialised technical skills. This has resulted in faster decision-making, improved operational efficiency, and enhanced customer experiences for Nasdaq.
Similarly, in the life sciences sector, healthcare organisations are using Amazon Q to empower clinicians and administrators to quickly identify trends in patient outcomes, monitor the effectiveness of treatment protocols, and optimise resource allocation. Gilead Sciences, a leader in biopharmaceutical innovation, has seen Amazon Q as a key driver of faster insights generation and analysis, enabling them to accelerate advancements in medicine.
The marketing industry has also benefited from the data storytelling capabilities of Amazon Q. Wunderkind, a leading digital marketing platform, has been able to bring a new level of efficiency to its customer success and marketing teams by leveraging Amazon Q to surface insights from its vast proprietary data. This has empowered Wunderkind’s business users to service clients faster and with greater accuracy, while also accelerating the content creation process.
The future of Amazon Q
The future of Generative BI and Amazon Q within the QuickSight platform holds great potential. As the capabilities of Generative BI continue to evolve, we can expect to see advancements in natural language processing, predictive analytics, and deeper integration with other enterprise systems. These developments will further empower business users to unlock valuable insights from their data, changing the way organisations approach decision-making, and a shift in the role of IT and BI teams.
To conclude
As you’ve seen, by empowering non-technical users to become collaborative data storytellers, Amazon Q has helped to bridge the gap between complex data systems and the need for actionable insights.
As an AWS Specialist Data and AI Partner, Firemind is uniquely positioned to help businesses leverage the power of Amazon Q and Amazon QuickSight to drive meaningful business outcomes.
To learn more about how Amazon Q and QuickSight can transform your organisation’s data analytics capabilities, reach out using the form below.
Get in touch
Want to learn more?
Seen a specific case study or insight and want to learn more? Or thinking about your next project? Drop us a message!
Explore latest insights from Firemind
View all
Cassio Milani joins Firemind as an Senior Solutions Architect
Personalising Retail Experiences with Generative AI: Beyond Recommendations
