
Step Functions as AI Agent Tools: The Model Decides When, the Workflow Decides How
AgentCore Gateway now exposes Step Functions workflows as MCP tools. Operations, pinning, task tokens, IAM gotchas, real CLI code and pricing.
Tag archive

AgentCore Gateway now exposes Step Functions workflows as MCP tools. Operations, pinning, task tokens, IAM gotchas, real CLI code and pricing.
![[AWS] Using Step Functions as an agent tool: Testing how PINs, IAM, and tokens work [AgentCore]](https://media2.dev.to/dynamic/image/width=1000,height=420,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Fl1sc2w5n03sa7sgrygf1.jpg)
This article is a machine translation of the contents of the following URL, which I wrote in...

Part of the FSx for ONTAP S3 Access Points serverless patterns series The update this...
Most developers reach for a Lambda function every time they need an LLM response, adding unnecessary...

Write a Step Functions workflow as a Python function, and get the state machine definition you might have written by hand.
AI agents are often portrayed as needing custom servers and endless glue code. In reality, the entire...
Sending every request to your biggest model is the easiest way to burn a Bedrock budget — a "what's...

Ask any AWS team how they ended up on Step Functions and you'll get the same answer: it was already...
Originally published in AWSBuilder The hardest problem in AI-driven operations is not getting an...

Introduction Hi, I'm miruky. Not every workflow decision needs a Lambda function. An AWS...
TL;DR A daily pipeline fetches 24 curated RSS feeds, clusters items describing the same...
Originally published on the AWS Builder Center: ...