AIToday
Large Language ModelsOpen-Source AIAmazon AI BlogPublished: Nov 12, 2026, 06:00 JST

AWS opens 23 reusable genAI assets, cuts dev time to weeks

Send on LINE
AWS opens 23 reusable genAI assets, cuts dev time to weeks

3 Key Points

  1. What happened

    AWS's Generative AI Innovation Center released 23 production-ready open source assets. DoorDash used the Contact Center GenAI Agent to handle over 100,000 calls per day with 2.5-second latency, and Ricoh achieved a 7-fold throughput increase, from 10,000–70,000 documents monthly.

  2. Why it matters

    Teams building generative AI solutions can start from validated, security-reviewed building blocks instead of rebuilding RAG pipelines and document processors, potentially saving weeks of engineering work.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, every morning.

Context & Analysis

The AWS Generative AI Innovation Center has been publishing open source reusable assets since 2023, and the catalog now includes 23 production-ready building blocks. The post identifies three root causes for redundant development: assets scattered across repositories, no quality signal for production readiness, and an informal reuse culture. By providing validated, security-reviewed assets with deployment guides, AWS aims to reduce the undifferentiated heavy lifting that delays customer delivery. The customer examples illustrate the potential impact: DoorDash built a voice-operated contact center solution using the Contact Center GenAI Agent, and Ricoh standardized multi-tenant document processing with the Accelerated Intelligent Document Processing asset. These results suggest that reusable assets can shift engineering effort from infrastructure to business logic, though the extent of savings likely depends on how closely a team's needs match the available assets.

FAQ
What kind of assets are in the AWS catalog?
The catalog includes RAG pipeline components, document processors, agent scaffolding templates, evaluation frameworks, and prompt management patterns.
How much time can teams save by using these assets?
AWS says the assets can reduce development time from months to weeks. DoorDash reached live testing readiness in 2 months, and Ricoh cut onboarding time from 4–6 weeks to 2–3 days.
Are the assets free to use?
Yes, the assets are open source and available on GitHub and AWS Labs.
Amazon AI BlogRead Original Article
Send on LINE

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.

Questions and answers are published on this page.

Related Articles

Next articleAnthropic IPO video: Claude runs on all four chip families