# Automating agentic AI Well-Architected reviews with the AWS Agentic AI Lens

DevFeed: [Automating agentic AI Well-Architected reviews with the AWS Agentic AI Lens](<https://devfeed.tech/articles/automating-agentic-ai-well-architected-reviews-with-the-aws-agentic-ai-lens-105408.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/architecture/automating-agentic-ai-well-architected-reviews-with-the-aws-agentic-ai-lens/>)

Author: Dinesh Subramani

Published: 2026-10-28T18:25:50Z

Content type: article

Language: en

Sources: [AWS Architecture Blog](<https://devfeed.tech/sources/aws-architecture-blog.md>)

Topics: [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [audit](<https://devfeed.tech/topics/audit.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [Amazon Web Services](<https://devfeed.tech/topics/aws.md>), [Integration testing](<https://devfeed.tech/topics/integration-testing.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [all](<https://devfeed.tech/tags/all.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-well-architected](<https://devfeed.tech/tags/aws-well-architected.md>), [aws-well-architected-framework](<https://devfeed.tech/tags/aws-well-architected-framework.md>), [best](<https://devfeed.tech/tags/best.md>), [best-practices](<https://devfeed.tech/tags/best-practices.md>), [claude](<https://devfeed.tech/tags/claude.md>), [console](<https://devfeed.tech/tags/console.md>), [customer-solutions](<https://devfeed.tech/tags/customer-solutions.md>), [days](<https://devfeed.tech/tags/days.md>), [first](<https://devfeed.tech/tags/first.md>), [framework](<https://devfeed.tech/tags/framework.md>), [github](<https://devfeed.tech/tags/github.md>), [github-repository](<https://devfeed.tech/tags/github-repository.md>), [instead](<https://devfeed.tech/tags/instead.md>), [intermediate-200](<https://devfeed.tech/tags/intermediate-200.md>), [lens](<https://devfeed.tech/tags/lens.md>), [reviews](<https://devfeed.tech/tags/reviews.md>), [with](<https://devfeed.tech/tags/with.md>)

## AI overview

Smarsh turned the AWS Agentic AI Lens into a repeatable Claude skill because the published lens--150 best practices across 41 questions and six pillars--was not yet selectable in the Well-Architected console. It reads a workload's GitHub repository, applies evidence and status rules, then uses a validating Python script to generate a standardized workbook with cited evidence, gaps, remediation, and live summary formulas. On synthetic repositories, the skill passed all 16 evaluation expectations; reviews without it passed 8 of 16 and produced incomplete checklists. The first real review took hours and found both safeguards and high-risk gaps, including disabled gateway authentication, missing prompt-injection screening, unfinished rate limiting, and absent automated cost controls. Human reviewers validated and reprioritized findings, while repository gaps about AWS service behavior informed a focused AWS Solutions Architect session. The article presents hours instead of days as an early internal result and describes broader approval and time-to-market benefits as expected outcomes.

## Source excerpt

Smarsh used the AWS Well-Architected Framework's Agentic AI Lens to review its first agentic workload. Because the lens is not yet selectable in the console, the team encoded it as a Claude skill that assessed all 150 best practices against the workload's GitHub repository and produced an evidence-backed review workbook in hours instead of days.