Cut AI token usage by 96%? Here’s how AWS Strands Agents does it.

About this episode

Morgan Willis discusses how AWS Strands Agents can significantly reduce AI token usage through efficient API design.

In this episode of The New Stack Makers, AWS developer advocate Morgan Willis demonstrates Strands Agents, an open source agentic framework with rapid adoption since its launch. Using a simple accounting API, she walks through three approaches to retrieving a customer’s latest invoice, highlighting how design choices dramatically impact efficiency. The initial method maps each API endpoint to a separate tool, requiring five chained calls and consuming about 52,000 tokens. By shifting to intent-based tools—focused on outcomes rather than individual data operations—the same task is completed in a single call using just 2,000 tokens, improving both efficiency and reasoning.

People in this episode

Host: The New Stack

Guest: Morgan Willis

Topics covered

• AI
• open source
• efficiency
• API design
• cloud computing

Keywords

• AWS
• Strands Agents
• API
• efficiency
• token usage
• open source
• accounting

Mentioned in this episode

Organizations: AWS, The New Stack

Products: Strands Agents

More episodes of The New Stack Podcast

• WeAreDevelopers is coming to the US to give unsung developers a bigger voice · June 11, 2026 · 50 min
• Why MotherDuck refuses to fork DuckDB · May 27, 2026 · 28 min
• JetBrains is selling independence as the rest of AI coding picks sides · May 21, 2026 · 26 min
• Why Block handed Goose to the Linux Foundation · May 15, 2026 · 20 min
• Fivetran's CPO: closed data stacks won't survive the agent era · May 13, 2026 · 23 min
• The new FinOps problem isn't cloud bills · May 12, 2026 · 28 min