Official announcement · AWS Machine Learning ·
Accelerating generative AI delivery with reusable assets

Every generative AI team keeps rebuilding the same components: RAG pipelines, document processors, and agent scaffolding.
In this story
- Repoaws-samples/contact-center-genai-agent
- Repoaws-solutions-library-samples/accelerated-intelligent-document-processing-on-aws
- Repoawslabs/fullstack-solution-template-for-agentcore
- Repoaws-samples/sample-agentic-chatbot-accelerator
- Repoaws-samples/sample-multi-lingual-document-processor
- Repoaws-samples/intelligent-document-processing-with-amazon-bedrock
- Repoaws-samples/extract-info-from-complex-docs-with-amazon-bedrock
- Repoaws-samples/amazon-comprehend-automated-pdf-prelabeling-tool
- Repoaws-samples/amazon-transcribe-live-call-analytics
- Repoaws-samples/amazon-transcribe-post-call-analytics
A tool or model opens in the Heidelberg AI Curriculum: what it does, what it costs, how to start. A repo opens on GitHub.



