This post walks through how Baz built their Spec Review agent using Amazon Bedrock and Amazon Bedrock AgentCore. We’ll cover the architecture decisions, implementation details, and the business outcomes they achieved by leveraging these AWS services to automate their code review process

Baz is built to move beyond traditional, diff-only reviews and toward validating whether a feature meets its intended product requirements. Early on, Baz saw that teams struggled with reviews that focused on syntax rather than behaviors, leaving critical questions like “does it work”, “does it match the spec”, “does it behave as intended”, to be answered manually and late in the process. This gap between code and product intent slowed the team down, created design inconsistencies, and required a heavy reliance on undocumented QA internal knowledge Baz set out to close this gap by building agents that could evaluate not just code, but the actual delivered experience.

The Baz Spec Review agent orchestrates a sophisticated multi-stage validation pipeline: Upon trigger (webhook or manual invocation), it concurrently queries Figma via MCP and Jira through REST APIs to aggregate comprehensive requirement artifacts spanning technical, product, and design specifications. The system then spawns isolated sub-agent workers (one per requirement) tasked with the job of verifying the requirement. This subagent combines code checking via the source code repository with dynamic runtime validation using Amazon Bedrock AgentCore Browser Tool. The subagent interacts with temporary environments, performing DOM inspection, event simulation, and visual testing to ensure the deployed implementation matches both Figma design specifications and behavioral requirements, delivering end-to-end verification across the entire specification-to-implementation lifecycle through AWS native orchestration

The following diagram illustrates the Spec Reviewer architecture, a joint solution from Baz and AWS that enables automated design and product validation within your code review workflow. The entire agentic flow is powered by large language models served through Amazon Bedrock, providing scalable and secure AI inference throughout the pipeline. The flow begins when a GitHub webhook triggers on a new pull request, routing traffic through an Application Load Balancer (ALB) and Network Load Balancer (NLB) into an Amazon EKS cluster. The Baz Platform serves as the central orchestration layer, coordinating the multi-agent review process.

Within the Amazon EKS cluster, Baz’s Spec Review Agent breaks down the validation workflow into specialized subagents. The Specification Subagent, powered by Amazon Bedrock, ingests both visual specifications from Figma and functional specifications from Jira, then decomposes them into discrete requirements – visual requirements (such as spacing, colors, and component hierarchy) and functional requirements (such as acceptance criteria and user story intent).