Data Analysis with Natural Language—No SQL Required: Amazon Quick
- 7 days ago
- 5 min read
Data Analysis with Natural Language—No SQL Required: Amazon Quick
Written by Minhyeok Cha
Introduction
Do you actively use BI dashboards in your daily work?
If a question such as, “Which channel had the highest conversion rate among new customers last quarter?” comes to mind, you would typically need to request support from a data analyst, write SQL queries, build a dashboard, and wait for the results.
Depending on the complexity, this process could take anywhere from a few hours to several days.
However, this is no longer the case. With AI-powered natural language prompts, Amazon Quick enables users to receive answers—along with visualized charts—within a matter of minutes.
Launched by AWS in 2026, Amazon Quick integrates generative AI into business intelligence. Even without SQL knowledge or dashboard-building experience, users can complete data analysis simply by asking questions in natural language.
While I do not have deep expertise in data analysis, I wrote this article to explore and learn about it together.
What is Quick?
Amazon Quick is a BI (Business Intelligence) tool built on top of Amazon QuickSight, enhanced with Kiro.
In addition to the visualization capabilities provided by Amazon QuickSight, it further improves user productivity through AI-driven data analysis.
Users can upload data files directly or connect AWS data services, and build dashboards through conversational natural language prompts in a chatbot-like interface.
Since Amazon Quick is based on Amazon QuickSight, it allows users to leverage AI on existing BI datasets and dashboards. It also supports integration with various applications to retrieve data and execute tasks.
💡 Amazon Quick provides chat, agent, and research features with integrated web search capabilities. However, cross-region web search is currently supported only in the following four regions:
- US East (Northern Virginia)
- US West (Oregon)
- Asia Pacific (Sydney)
- Europe (Ireland)
As Amazon Quick is built on the existing QuickSight platform, it enables the use of AI on BI datasets and dashboards. In addition, it supports integration with various applications to import data and perform tasks.
Key Features of Quick
💡 Prior to the demo, the dataset used in this example consists of website visitor patterns aggregated over a one-week period.
(1) Chat Agents
Chat Agents are conversational AI assistants that enable users to explore data, analyze information, and perform tasks through natural language interactions.
Unlike traditional chatbots, which rely on preloaded datasets to process prompts, Chat Agents provide a more contextual and flexible approach by interpreting prompts based on the underlying data.
In addition, each chat room can be configured with a unique chatbot persona, defined through a dedicated prompt.
Additionally, Amazon S3 was connected as a knowledge source to enable continuous data updates, and a simple chatbot was configured accordingly.
The following query was then submitted to the chatbot:
“Identify user acquisition channels and determine user needs (pages).”
As defined in the persona, the system effectively generates tables and provides suggestions for further analysis.
(2) Spaces
Spaces is a feature that consolidates files, dashboards, topics, knowledge bases, and application actions into a unified, customizable knowledge hub.
The connection between Spaces, the knowledge base, and Amazon S3 was preconfigured, as it is required for chatbot setup.
The structure of Spaces is outlined as follows.
Whether through file uploads, the knowledge base, or task actions, the system retrieves data from local environments or SaaS solutions and utilizes the dataset to execute prompt-based tasks.
Afterward, a Space can be added and used in the same manner as configured for the chatbot.
💡 For dashboards and topics, information can be imported into the relevant Space based on analyses performed in QuickSight. However, as this article focuses on Quick testing, the dashboard configuration process has been omitted.
(3) Quick Flows
Quick Flows is a workflow automation feature designed to streamline and automate repetitive or routine tasks.
Business users can create automations within seconds using simple, natural language prompts, without requiring technical expertise.
As the dataset in this example relates to website access patterns, the process proceeds by creating a Flow prompt as shown below.
The flow steps are automatically configured based on the input.
The prompt, “Retrieve the statistics compiled for the last week of February,” was then entered and executed.
The results of the report generated by the flow are as follows.
As it was defined as a weekly report, the system schedules report generation every Monday at 9 a.m. Even if the timeframe is not explicitly specified in the prompt, the schedule settings can be adjusted as needed.
💡 Recommended examples for first-time Flow users
- Automate tasks such as generating RFP responses, reviewing Statements of Work (SOW), and compiling the latest industry trends into sales materials
- Share workflows with individuals and teams across the organization
- Create predictable and reusable flows using predefined steps such as data retrieval, task execution, and content generation
(4) Quick Research
Quick Research is an AI-powered agent that analyzes multiple data sources to conduct comprehensive research and generate detailed reports.
Starting from a simple prompt, the tool automatically generates a structured research framework outlining the approaches and data sources required for in-depth analysis.
By combining internal organizational knowledge with publicly available internet data, it delivers expert-level insights in minutes rather than weeks.
After entering the prompt, “Based on the dataset in Spaces, what steps should be taken to increase customer engagement and retention rates?” and selecting “Start Research,” the following guidance was generated.
As the dataset covered a 7-day period, it was initially considered less suitable for analyzing engagement and retention rates. However, Quick Research extended the scope of the analysis and provided statistical visualizations combining data such as age, gender, annual income, Spending Score, monthly visit frequency, and preferred product categories.
In this way, the tool compiles reports based on the specific insights users wish to explore. Additionally, the research interface includes options for adding comments and generating summaries, enabling users to further refine and enhance the quality of the output.
Conclusion
One of the most significant strengths of Amazon Quick is its embedded dashboards. Rather than limiting analytical insights to a single user, it enables stakeholders across the organization to make decisions based on a shared dataset.
While this article focuses on integrations within AWS services, Amazon Quick also supports connectivity with a wide range of SaaS solutions, including Jira, Slack, and Salesforce. By unifying business intelligence and automation capabilities within a single platform, it allows users to manage workflows efficiently without switching between multiple applications.
Although Amazon Quick is still in its early stages, its vision of integrating research, analysis, and automation into a unified, AI agent–driven environment is clear. For organizations seeking to streamline workflows within the AWS ecosystem, the continued evolution of the Quick Suite is well worth monitoring.
