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

Page: https://stenobird.com/podcast/the-new-stack-podcast-1092634/cut-ai-token-usage-by-96-here-s-how-aws-strands-agents-does-it
Text version: https://stenobird.com/podcast/the-new-stack-podcast-1092634/cut-ai-token-usage-by-96-here-s-how-aws-strands-agents-does-it.md
Podcast: [The New Stack Podcast](https://stenobird.com/podcast/the-new-stack-podcast-1092634)
Published: 2026-04-29T17:00:00+00:00
Episode link: https://thenewstack.simplecast.com/episodes/cut-ai-token-usage-by-96-heres-how-aws-strands-agents-does-it-4eL8vcdi
Audio file: https://cdn.simplecast.com/media/audio/transcoded/317e9dbc-9a52-4da7-9725-c4578874b757/5672b58f-7201-4e0e-b0af-da702259d97f/episodes/audio/group/58ac87af-7f3c-4a29-a313-28faf7373e3d/group-item/01d22618-d502-469b-8e66-b9b792ed6982/128_default_tc.mp3?aid=rss_feed&feed=IgzWks06
Processing state: not_requested
JSON: https://stenobird.com/v1/public/podcasts/the-new-stack-podcast-1092634/episodes/cut-ai-token-usage-by-96-here-s-how-aws-strands-agents-does-it
Duration seconds: 1686

## Resource

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.

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/the-new-stack-podcast-1092634/episodes/cut-ai-token-usage-by-96-here-s-how-aws-strands-agents-does-it/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/the-new-stack-podcast-1092634/cut-ai-token-usage-by-96-here-s-how-aws-strands-agents-does-it.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.