PC Slower Than It Used to Be?
A free scan shows the junk files, broken settings and background clutter dragging Windows down - then fixes them in one click.Free scan · Windows 10 & 11Crashes, No Sound, or Screen Glitches?
Random freezes, missing sound and display glitches usually trace back to one bad driver. Find and replace yours safely.Free scan · under a minuteUse Kiro CLI to prepare and orchestrate an AWS Well-Architected review—not to replace AWS’s review services or produce a certified assessment on its own. For an existing workload, automate around the AWS Well-Architected Tool’s workload and lens-review APIs. For a pre-deployment infrastructure-as-code check, use the AWS Well-Architected Agent’s architecture-review path. Kiro can inspect inputs, run repeatable prompts, and coordinate a pipeline; AWS supplies the review criteria and results.
Can you automate an AWS Well-Architected review?
Yes, but automation supports rather than removes the review process. AWS describes a Well-Architected Framework Review (WAFR) as answering foundational questions about how an architecture aligns with cloud best practices and receiving guidance for improvements. Its process is Prepare, Review, Improve, so a useful workflow must account for workload context, stakeholder input, and follow-up on improvement items—not simply generate a report. AWS Well-Architected Framework Review.
As an Amazon Associate I earn from qualifying purchases.
Kiro CLI provides a repeatable workflow layer: it supports non-interactive prompts for CI/CD as well as project guidance, hooks, custom agents, skills, and MCP connections. It can help inspect infrastructure code, organize evidence, and hand off results. AWS’s services remain responsible for their own review criteria and operations. Kiro CLI documentation.
Choose the AWS review path first
The two AWS surfaces serve different purposes. Select the one that matches what you are reviewing before designing the Kiro workflow.
#1 Best Overall
| Aspect | Well-Architected Tool workload review | Well-Architected Agent architecture review |
|---|---|---|
| Best fit | An existing or documented workload review | A pre-deployment review of infrastructure-as-code |
| Input | Workload context, lens selection, and review answers | CDK or Terraform templates supplied from S3 |
| How it runs | Manage workloads and lens reviews through the Tool API or CLI | Manually start an architecture recommendation generation and poll its status |
| Review dimensions | Lens reviews; the Framework is commonly described through six pillars | The documented architecture-review operation lists COST_OPTIMIZATION, SECURITY, RESILIENCE, and PERFORMANCE as selectable values |
| Output and follow-up | Review findings, milestones, and improvement items | Recommendations with updated templates |
| Operational limit | Not stated in the cited Tool references | Five architecture reviews per day per profile, according to AWS documentation accessed in 2026 |
Sources: AWS Well-Architected Tool API Reference, AWS CLI Well-Architected reference, and AWS Well-Architected Agent architecture review.
For a workload review, use the Well-Architected Tool
Create or select the workload, associate the appropriate lens, collect answers and findings, then save milestones and track improvement items. The API and CLI support workload and lens-review management. Automating data entry or report handling does not replace preparation, agreement on the workload’s context, or the people who can verify its answers.
For an IaC check before deployment, use the Well-Architected Agent
The documented Agent path accepts CDK and Terraform templates staged in S3, uses the Framework lens, and returns recommendations with updated templates. Its architecture reviews are manually started; they are distinct from scheduled resource or application recommendation generation. AWS describes the Agent as preview in its API reference, so verify availability for your account and Region before building a dependency on it. The architecture-review API’s selectable values are not a claim that this operation covers every Framework pillar.
Build a repeatable Kiro-assisted workflow
- Put shared review guidance in the project. In a project-level Kiro steering file, specify workload or application context, the AWS review surface and lens, the evidence format expected, and how the agent should mark unknowns rather than infer answers. Kiro project settings live under
.kiro/; agent configuration lives under.kiro/agents/. Configuration precedence varies by feature, so verify which scope controls each setting. Kiro CLI steering and Kiro CLI configuration. - Use Kiro to inspect, not invent, review evidence. A custom agent or prompt can inspect IaC and supplied workload material, organize evidence against the chosen review, and flag missing facts for an engineer or stakeholder. Keep findings traceable to source files or confirmed workload answers.
- Let the pipeline call the AWS review surface. For workload reviews, use the Well-Architected Tool API or CLI operations. For architecture reviews, stage the templates in S3, start the Agent operation, capture its generation identifier, and poll generation status. Store outputs as build artifacts or review issues so engineers can examine recommendations.
- Keep a human review step. Have engineering and architecture stakeholders check generated assessments and recommendations before treating them as decisions. Track accepted work through the appropriate workload improvement process; do not automatically apply returned infrastructure changes.
Kiro’s headless mode supports prompts in CI/CD, and its hooks, agents, and MCP connections can make the workflow repeatable. Those capabilities do not establish a published time-saving, coverage, or risk-reduction result for this combined setup.
Rank #3
Connect AWS access safely in Kiro CLI V3
Kiro CLI V3 removed its built-in aws_tool. A previous agent configuration that depended on it should not be assumed to work. Use an AWS MCP server or keep AWS CLI/API calls in the surrounding pipeline and give Kiro scoped local files and captured results instead. AWS’s migration guide uses @aws/aws-mcp-server as an example and describes passing AWS profile and Region settings. Check package provenance, authentication, permissions, and version compatibility before production use. Kiro CLI V3 migration guide.
For Agent API use, AWS says execution and target-account access roles must be created before API use; the API does not create them. A profile defines selected pillars and account/Region aggregation, while goals and application context can tailor recommendations. Check profile eligibility before relying on scheduled generation. AWS Well-Architected Agent API reference and AWS Well-Architected Agent quickstart.
- Give the review job only the AWS permissions needed for its selected path, and keep review roles separate from deployment roles.
- Use explicit permissions for MCP tools and Kiro agents; avoid exposing credentials in prompts or repository files.
- Validate access and outputs with a limited profile before enabling the workflow broadly.
- Require an authorized human to review generated infrastructure changes before deployment.
These are safeguards for combining role-based AWS access with configurable Kiro tools; the cited sources do not prescribe one universal IAM policy for every combined workflow.
Account for Agent input limits
AWS’s architecture-review documentation sets these input constraints. They are service limits, not performance claims.
Best Value
- A ZIP archive can be no larger than 25 MB.
- An S3 folder can total no more than 100 MB, and no individual file can exceed 1 MB.
- The S3 bucket Region should match the Agent profile Region.
- A profile can run five architecture reviews per day, according to AWS documentation accessed in 2026.
Source: AWS Well-Architected Agent architecture review.
Run the AWS Well-Architected Tool from the AWS CLI
The AWS CLI reference exposes Well-Architected Tool operations for managing workloads and lens reviews. Use the reference that matches the installed AWS CLI version to choose commands, then have the pipeline capture identifiers and results for review. Kiro can prepare inputs or interpret saved output, but it does not turn those operations into a different or more authoritative AWS review. AWS CLI Well-Architected command reference.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
Recommended Free Tools
