Skip to content

feat(01-learn): add 19-multi-model tutorial#269

Open
vediyappan-kk wants to merge 1 commit into
strands-agents:mainfrom
vediyappan-kk:feat/19-multi-model
Open

feat(01-learn): add 19-multi-model tutorial#269
vediyappan-kk wants to merge 1 commit into
strands-agents:mainfrom
vediyappan-kk:feat/19-multi-model

Conversation

@vediyappan-kk

Copy link
Copy Markdown

Adds Multi-Model Agent Patterns tutorial to python/01-learn/

Covers:

  • Runtime provider switching (agent.model = new_model)
  • Sequential multi-agent pipeline (researcher → summarizer)
  • Agents-as-tools with heterogeneous models
  • Cross-provider coordination (OpenAI/Anthropic optional, Bedrock fallback)
  • CostRouter: rule-based complexity classification → model selection
  • FallbackHandler: ordered provider chain with automatic retry
  • Simulated failure demos (throttling, timeout, all-fail)

Tested on SageMaker Studio with strands-agents and Claude Sonnet 4.5, Nova Lite, Nova Pro

@vediyappan-kk

Copy link
Copy Markdown
Author

@manoj-selvakumar5 This is ready for review. It;s for Tutorial 19: Multi-Model Agent Patterns.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant