---
title: "Automating agentic AI Well-Architected reviews with the AWS Agentic AI Lens"
description: "Smarsh, a compliance platform, needed to review its first multi-agent workload against the AWS Well-Architected Framework’s Agentic AI Lens, which existed only as published documentation with 150 best practices. To avoid a multi-day manual effort, Smarsh built a custom Claude skill that treats the lens as structured data and automates evidence gathering from the workload’s GitHub repository. The skill uses a five-value status rubric, honesty rules, and a deterministic Python script to produce a formatted workbook with per-item status, evidence, gaps, and remediation. Smarsh validated the skill against two synthetic fixture repositories—a moderately mature workload and a deliberately rough proof of concept—achieving 16 of 16 verifiable expectations, compared to 8 of 16 without the skill; the evaluation suite ships inside the skill for ongoing regression testing. The resulting reviews enabled sharper AWS engagement by mapping specific best-practice gaps to focused working sessions with AWS Solutions Architects."
---

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

[AWS](https://yomu.fyi/company/aws) · Dinesh Subramani · Oct 28, 2026

**Type:** Problem & solution

## Summary

Smarsh, a compliance platform, needed to review its first multi-agent workload against the AWS Well-Architected Framework’s Agentic AI Lens, which existed only as published documentation with 150 best practices. To avoid a multi-day manual effort, Smarsh built a custom Claude skill that treats the lens as structured data and automates evidence gathering from the workload’s GitHub repository. The skill uses a five-value status rubric, honesty rules, and a deterministic Python script to produce a formatted workbook with per-item status, evidence, gaps, and remediation. Smarsh validated the skill against two synthetic fixture repositories—a moderately mature workload and a deliberately rough proof of concept—achieving 16 of 16 verifiable expectations, compared to 8 of 16 without the skill; the evaluation suite ships inside the skill for ongoing regression testing. The resulting reviews enabled sharper AWS engagement by mapping specific best-practice gaps to focused working sessions with AWS Solutions Architects.

## Context

The Agentic AI Lens from the AWS Well-Architected Framework existed only as published documentation with 150 best practices, not as a selectable lens in the console. Smarsh needed to conduct a rigorous, evidence-based review of its first multi-agent workload for regulated customers but faced a multi-day manual effort or waiting for console support.

## Approach / What changed

Smarsh built a custom Claude skill that packages the lens as structured JSON data (lens\_data.json), an assessment guide with a five-value status rubric and honesty rules (assessment-guide.md), and a deterministic Python script (build\_report.py) to generate a formatted workbook. The skill reads the target GitHub repository for evidence, assesses all 150 best practices, and produces a standardized review workbook with per-item status, evidence, gaps, and remediation.

## Takeaways

- The Agentic AI Lens contains 150 best practices across 41 questions and six pillars, with risk levels: 90 High, 59 Medium, and 1 Low.
- Smarsh’s Claude skill uses a five-value status rubric (Compliant, Partially Compliant, Non-Compliant, Not Applicable, Not Reviewed) and requires evidence citation for every definitive status.
- The skill was validated against synthetic fixture repositories, passing 16 of 16 verifiable expectations, while baseline runs without the skill passed only 8 of 16.

## FAQ

### How did Smarsh make the Agentic AI Lens executable?

Smarsh built a custom Claude skill that treats the lens as structured data (lens\_data.json), uses an assessment guide with honesty rules, and runs a Python script to generate a formatted workbook. The skill pulls evidence from the workload's GitHub repository.

### What validation did Smarsh perform on the skill?

Smarsh created two synthetic fixture repositories and ran reviews with and without the skill. With the skill, all 16 verifiable expectations were met; without it, only 8 of 16 passed. The evaluation suite ships inside the skill for regression testing.

### How did the automated review improve AWS engagement?

The review surfaced system-semantics questions that no repository could answer, allowing Smarsh to build a focused agenda for AWS Solutions Architects, mapping each question to a specific best-practice gap for a working session with a definition of done.

**Tags:** [AI Agents](https://yomu.fyi/topic/ai-agents), [Amazon Bedrock](https://yomu.fyi/topic/amazon-bedrock), [AWS](https://yomu.fyi/topic/aws), [Claude](https://yomu.fyi/topic/claude), [Well-Architected](https://yomu.fyi/topic/well-architected)

- Source: [AWS](https://aws.amazon.com/blogs/architecture/automating-agentic-ai-well-architected-reviews-with-the-aws-agentic-ai-lens)
- Source URL: https://aws.amazon.com/blogs/architecture/automating-agentic-ai-well-architected-reviews-with-the-aws-agentic-ai-lens
- Ingested by Yomu: 2026-10-28T21:00:17.592Z

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