AWS Turns 18-Tab Excel Model Into AI Chatbot for Deal Pricing

AWS replaced an 18-tab Excel model for evaluating customer deals with an AI chatbot that answers pricing questions in natural language, according to AWS SVP and CFO John Felton. The change did not simply make the old tool easier to use — it changed how employees interact with the underlying analysis.

The pricing team's spreadsheet let analysts work through deal scenarios across 18 separate tabs. The chatbot interface now lets them ask plain questions instead: what happens if a price falls 20%, how different payment terms affect a deal, or where the break-even point lies. Employees who prefer the original format can still export the model to Excel.

Felton described the shift to Fortune. The story, originally featured on Fortune.com, draws on his conversation with Fortune's Sheryl Estrada.

What does the chatbot replace?

The 18-tab Excel model sat at the center of AWS's customer-deal evaluation process. Converting it into a chatbot removed the manual navigation between tabs and turned scenario analysis into a conversation. Analysts query outcomes directly rather than rebuilding calculations.

The team kept a fallback. Anyone who wants the spreadsheet can export the model back to Excel, so the tool expands access rather than forcing a switch.

A second AI agent checks every contract, not a sample

Another AWS team built an AI agent that compares payment terms in customer contracts against the terms recorded in AWS's payment system. Previously, employees audited a sample of contracts. The agent checks all of them.

"Let's not just do a sample size, let's do all of it," Felton said, describing the team's approach.

The two projects illustrate what Felton sees as the broader move in corporate AI strategies: using the technology not only to speed up existing work, but to expand what the organization can do.

How big is the business behind this?

AWS is now a $169 billion annualized business. Felton has spent more than 20 years at Amazon and previously led Amazon's worldwide operations. He became AWS finance chief in 2024 and reports to Amazon CFO Brian Olsavsky.

His vantage point matters because AI is driving a significant new investment cycle across the industry, and Felton speaks regularly with AWS customers, including fellow CFOs, about their adoption plans.

Where do customers stand on AI adoption?

Adoption remains uneven, Felton said. Many AWS customers are still early in their broader cloud and IT modernization efforts — a prerequisite for deploying AI at scale.

"I think in general, I would say it feels early across the board," Felton said. "It's unbelievable the pace of change, how fast things are moving. I do think every company is in a different stage of it. I think everyone is still early."

The conversation has also shifted direction. Two years ago, Felton said, customer AI discussions focused largely on productivity and cost cutting. That focus is changing.

"There really is a lot more focus on: how do I use AI for new revenue products, for new customer experiences?" he said.

What is the 'AI first mindset'?

The bigger shift, according to Felton, runs from adding AI to an existing process to rethinking the process itself. What impresses him is companies moving toward an "AI first mindset" — using AI to rethink what the business should be in the first place.

"That is where a bunch of customers, including ourselves, really see a lot more value," Felton said.

How does Felton push AI inside finance?

Inside AWS's finance organization, Felton tells employees not to wait for instructions. His guidance is straightforward: "Use AI every day."

He does not dictate which tasks employees should tackle or which tools they should use. Instead, he wants them to identify opportunities themselves, arguing they understand their own work better than he does. He tracks whether employees follow through, though he did not detail those metrics.

Felton practices what he prescribes. He uses Amazon Quick, an AI assistant for work, to query supporting materials prepared for board meetings and to locate answers in the underlying files. He sees that kind of everyday experimentation as important for CFOs figuring out where AI fits in their organizations.

The pricing chatbot and the contract-checking agent suggest the direction: the measurable wins come when teams stop optimizing old workflows and start asking what a full-coverage, conversational version of the work would look like.