All financial professionals know the principle. Monday morning arrives and your financial planning and analysis (FP&A) team disappears into data compilation. They pull numbers from multiple systems, reconcile sources, create graphs, and write commentary. All this to answer what should be a simple question: what happened with earnings last week and why?
At AWS Finance, teams were spending hundreds of hours per month on exactly this type of work. No analysis. No strategy. Prepare the data so the real work can begin.
Amazon Quick is a generative AI assistant that connects to all your business data and applications, so business users can search, analyze, and take action through natural language. It handles the complexity of querying millions of rows, running advanced analytics, and automating recurring workflows so your team doesn’t need it.
In this article, we show how AWS Finance used Chat Agents and Flows in Quick to transform two of their most time-consuming workflows.
Use case 1: Scenario modeling and risk analysis across the entire strategic portfolio
Setting financial goals for strategic customers requires reconciling bottom-up forecasts from sales teams with top-down projections from executives. It also requires enough depth to detect the risks behind historical data.
The team created an Amazon Quick chat agent that connects directly to enterprise data sources and delivers sophisticated insights through natural language conversation. The agent instantly queries millions of rows in Amazon Redshift data tables while also looking for external data signals.
Screenshot showing Quick presenting a scenario analysis and creating a 5-sheet Microsoft Excel spreadsheet.
Here’s what’s changed:
Before: Analysts could delve deeper into about a third of strategic customers in the time available between bottom-up input and when high-level goals are expected. The remainder benefited from surface level coverage. A single client analysis required up to 6 hours of manual work, including extracting data, running models, and documenting results.
After: The Quick Agent evaluates statistical forecasts, runs regression analysis, Monte Carlo simulations, and performs multi-factor scenario modeling in approximately 10 minutes per customer. It uncovers risks and opportunities that manual analysis missed. The team now covers its entire client portfolio with even greater depth than before.
“We’ve gone from in-depth analysis of a third of our strategic customers to covering our entire portfolio. Our finance team now spends time on what matters: partnering with the business to generate revenue, without compiling data or writing complex queries.”
—Geoff Winkler
What makes this work: An analyst asks a question in natural language: “Conduct an opportunity and risk assessment for our key strategic accounts.” Quick then queries millions of rows, runs advanced analytics, and synthesizes the structured data with unstructured information from field reports and pipeline data. The agent performs a bull versus bear analysis by reviewing accounts with upside potential based on contract renewal timing and pipeline strength, and flags accounts with risk exposure. This is information that traditional models have missed.
Since there are no coding barriers, every finance professional on the team becomes a data analyst. Teams customize agents for different regions or business units, and the information updates automatically.
Use Case 2: Weekly Business Reviews from 6 hours to 10 minutes
If goal setting is a periodic in-depth analysis, regular business reviews are the recurring ritual that keeps FP&A teams busy everywhere. At AWS, each week, revenue performance information must be compiled, analyzed, and aggregated for leadership. And each week, this preparation consumes an entire Monday.
The same AWS Finance team solved this problem by deploying region-specific Amazon Quick chat agents, connected via Flows to automate workflows that run at a set cadence without manual intervention.
Video showing a blank revenue performance review workflow that helps automate weekly business review workflows.
Here’s what’s changed:
Before: Every Monday, FP&A analysts spent an entire morning compiling data from multiple systems, analyzing trends, manually reaching out to prospects for customer stories, and preparing talking points so executives could understand what happened with revenue and why. The process was manual, repetitive and left little time for strategic work.
After: Quick automatically runs the Flow every Monday morning. Region-specific chat agents analyze revenue performance along several dimensions: by fee type, by customer segment, and by growth contribution. They prepare comprehensive information with ready-made discussion leads for leadership. A new analysis awaits before the start of the working day.
Quick doesn’t just report numbers. It connects structured data from financial systems to unstructured information from field reports to understand why trends occur. It examines customers across more than a dozen dimensions, identifies patterns, and flags anomalies with context.
“This information is prepared automatically every Monday morning. Our team now spends time on strategic priorities instead of compiling disparate data. We spend more time on why and delivering business results.”
—Geoff Winkler
The model: from data compilation to strategic partnership
These two use cases share a common thread. In both cases, the bottleneck was not analytical skill, but data compilation. Data was scattered between systems. Getting a complete picture required hours of manual extraction before real analysis could begin.
Amazon Quick removes this bottleneck by connecting directly to enterprise data sources and allowing finance professionals to interact with their data through natural language. The result is not additional efficiency. This is changing the way finance teams spend their time:
| Workflow | Before Amazon Quick | With Amazon Fast |
| Setting goals | Approximately 6 hours per client; a third of the portfolio covered | Approximately 10 minutes per client; the entire portfolio covered in more depth |
| Preparation of the weekly Business Review | Monday morning full of manual compilation and analysis | Automated every week; information ready before the start of the working day |
| Team Focus | Compiling data and writing queries | Strategic analysis and business partnership |
In these use cases, the AWS Sales and Marketing Finance team reduced goal setting time from 6 hours to approximately 10 minutes through in-depth customer analysis. They also completely removed the manual Monday routine for weekly trade journal preparation. The time recovered was directly reinvested in strategic work: risk analysis, synthesis of customer stories and identification of growth opportunities.
What this means for your finance team
You don’t need to deal with Amazon-scale complexity to benefit. Every finance team faces fragmented data, recurring reporting cycles, and the tension between compiling numbers and actually using them.
Amazon Quick is designed for business users. Finance professionals set up chat agents and automated workflows themselves, without technical assistance. They customize agents based on their specific needs, iteratively refining them, and rolling them out across the organization as results emerge.
If your team spends more time preparing information than delivering it, that’s the gap Quick is designed to fill.
Learn more about Amazon Quick for Finance.
In the next article in this series, we’ll explore how AWS Finance teams use Quick to automate cost optimization and streamline approval workflows, turning hours of manual analysis into minutes.
About the authors
Sindhu Chandra
Sindhu is a Senior Technology Product Marketing Manager at AWS, leading the go-to-market strategy for Amazon Quick. With over 15 years of experience at Amazon, Uber and Google, she is passionate about making technology marketing accessible, inclusive and based on real customer value. Outside of work, she enjoys playing with her dog and making coffee from different origins.
Sarah Oates
Sarah is a Senior Product Manager leading the AI tools strategy for AWS Finance. With over 13 years of experience at Amazon spanning operations, e-commerce, and machine learning, she is passionate about creating practical, grounded AI solutions with real business impact. She is the proud mother of two energetic children and a grumpy Italian Greyhound.
“`
