The Amazon Bedrock AgentCore service automates the creation of architectural documentation from code
AWS described a solution using the Amazon Bedrock AgentCore service that uses autonomous agents to analyze .NET code and automatically generate architectural diagrams and documentation integrated into CI/CD. It has been running in production since the 1st quarter of 2026 at a global financial firm focused on interdealer broking.
AWS described a solution on its blog built on the Amazon Bedrock AgentCore service that uses autonomous AI agents to analyze source code and automatically generate architectural diagrams and documentation. The goal is to address the problem of manually created documentation, which, according to AWS, quickly becomes outdated, creates knowledge silos, slows developer onboarding and complicates compliance audits.
The solution combines AgentCore for analyzing a .NET codebase, Amazon Bedrock Knowledge Bases for semantic search across documentation (with the Amazon Titan Text Embeddings embedding model and Amazon S3 as vector storage), and the AWS CodePipeline service for CI/CD integration triggered by every commit to AWS CodeCommit. An agent built on the Strands framework works through the code iteratively: it analyzes the structure of the codebase, generates class, sequence, state, component and activity diagrams in Mermaid format, validates their syntax and corrects any errors itself, then converts them to SVG format and publishes them to Amazon S3 storage.
According to AWS, the solution has been running in production since the first quarter of 2026 at a global financial firm specializing in interdealer broking, where it maintains architectural documentation for an electronic trading platform. Details can be found in the source article.
Why it matters
For development teams, especially in regulated industries such as financial services, the described solution shows a concrete way to automatically keep architectural diagrams synchronized with code without manual work – this makes onboarding and audit preparation easier. However, this is a single documented deployment case described by AWS itself, not an independently verified benchmark, so the source does not indicate how transferable it is to other technology stacks or industries.
Two audiences, two different impacts
What this means
For individuals
Developers on teams with similar architectures could have access to architectural diagrams that are always up to date and generated automatically with every commit, which should make it faster to navigate unfamiliar code and onboard new developers.
For a business
According to the case described by AWS, companies with older, large codebases may be able to reduce the costs of manually maintaining architectural documentation and simplify preparation for compliance audits – the solution has been validated in production at a financial firm specializing in interdealer broking.
DevelopmentCheck the original
Event sources
only one source so far · 1 publisher, 0 independent. We count feeds from the same owner only once.