About / Product Vision

EA2.0 ARB Copilot is a human-in-the-loop agentic AI product for enterprise architecture governance. It helps CIO/CTO offices and enterprise architecture teams convert technology intake requests into structured review analysis, routing recommendations, architecture risk discovery, missing information detection, NFR checklist generation, reviewer task routing, and audit-ready decision evidence.

Architecture, security, procurement, cloud, data privacy, and AI governance reviews are fragmented. Requests are often incomplete, review routing is manual, decisions are poorly documented, and audit evidence is created late or inconsistently.

EA2.0 ARB Copilot uses specialized AI agents to assist ARB teams:

• Intake Understanding Agent — Parses raw requests into structured systems, data, and assumptions.
• Classification Agent — Scores complexity and risk and proposes required and optional review domains.
• Risk Discovery Agent — Surfaces architecture risks with severity, likelihood, and suggested controls.
• Missing Information Agent — Detects gaps and drafts targeted questions for the requester.
• NFR Checklist Agent — Generates a non-functional checklist across security, privacy, integration, and operations.
• Routing Agent — Recommends ARB sub-teams and rationale based on the risk profile.
• Decision Evidence Agent — Synthesises a recommendation, conditions, and a draft ADR for the ARB.

AI agents recommend. Human ARB leads decide. Final architecture decisions remain accountable to authorized human reviewers.

AI / SaaS / software onboarding review.

• FrontendReact / Next.js
• Agent OrchestrationBackend service / workflow engine
• AI LayerClaude / Anthropic API, later Claude via AWS Bedrock
• Data LayerPostgres / DynamoDB
• StorageS3
• WorkflowStep Functions or equivalent
• Enterprise IntegrationsServiceNow, Jira, Freshservice, SharePoint, Ardoq, Bizzdesign