What changes
Before and after
The classic way
- Architecture is drawn in slides and reviewed in a meeting; the drawing and the cloud drift apart within weeks.
- Design reviews happen once, before the project; the system that goes live was never reviewed as built.
- Reliability, cost and security are separate checklists owned by separate teams.
The AI way
- Architecture is written as code and decision records, and an agent reviews each change against written principles. The AWS Well-Architected Generative AI Lens states six: design for controlled autonomy, implement comprehensive observability, optimize resource efficiency, establish distributed resilience, standardize resource management, and secure interaction boundaries [7].
- Google SRE's own account describes agents that help make reliability part of system design through the design, launch and deployment phases, where a number of issues can be detected and auto-addressed before they need to be reviewed by a person [3].
- Infrastructure is generated and validated with no cloud credentials before it is ever applied; the validation ladder is shown, with real runs, in the test center [14].
Step by step
The three steps of Architect
- 1
The agent proposes a design AI
From the spec, an agent drafts the architecture: services, data flows, trust boundaries, the cloud resources as code, and a first threat model of where untrusted input meets a tool.
- 2
Principles review it AI
A second pass checks the design against written principles, the six of the AWS Generative AI Lens among them, and against the organization's own decision records [7].
- 3
An architect decides Gate
A person signs the decision record. Controlled autonomy is the first of the Lens's principles for a reason: the boundaries of what the system may do are set here, by people [7].
The gate
An architecture decision record signed by a person, with the trust boundaries and the agent's permissions written down before a line of infrastructure is applied.
What the AI does here
Drafts the design and the infrastructure code, reviews changes against principles, keeps diagrams generated from the code so they cannot drift.
Tools people use at this stage
- Terraform and OpenTofu
- AWS Well-Architected Tool
- Checkov
- Conftest and OPA
- Claude Code
Named as examples, not endorsements; the center is not affiliated with any of them.
What this stage adds
The risks, and the practices that answer them
Each risk is a weakness in the Learning Center, with the incidents where it happened; each practice has its sources there.
Risks
- Agents with standing write access to productionThe design gives an agent standing write access it should never have.
- Unrestricted network egress for agentsEgress is left open because nobody drew the boundary.
- Exposed AI infrastructure without authenticationAI infrastructure reaches the internet without authentication.
Read for this stage