[FEATURE] Set up a dynamic map-reduce graph in Strands

[Nicricflo]

Problem Statement

I would like to understand the proper way to set up a map-reduce graph framework in Strands. I am used to using the Send api from langgraph (see https://docs.langchain.com/oss/python/langgraph/graph-api#send for reference).

Basically, at runtime, depending on the users query, I would like anywhere from 1-5 sub-agents to be spawned (depending on user query complexity) to perform various tasks (in parallel). What would be the best way to accomplish this with strands?

Proposed Solution

No response

Use Case

This would help with map-reduce workflows (like summarizing a long document, where each agent takes a large chunk of documents, summarizes it, and a "summary of summaries" is created by the final agent. You don't know beforehand how many agents will be deployed.

Alternatives Solutions

No response

Additional Context

No response