Architecture and delivery systems
AI-Augmented Software Delivery
Designing agentic engineering workflows where AI agents, engineers, review, testing and delivery work together.
2025-presentPublic-safe process case studyAI agentsMCPGitHubCI/CDTesting
The Challenge
AI coding tools are useful only when they fit the engineering system around them. The hard part is not asking a model to write code; it is connecting intake, context, implementation, review, tests, approvals and deployment without weakening accountability.
My Role
I design human-in-the-loop workflows where agents can research, implement and verify scoped tasks while engineers retain architecture, review and release responsibility.
- Build reference architectures and sample code for AI developer tools.
- Bring developer feedback directly into product and engineering teams.
- Deliver deep technical talks and builder enablement for teams adopting AI-assisted delivery.
Architecture And Approach
- Keep repository knowledge in reusable instructions and skills.
- Give agents tool access through explicit MCP and local workflows.
- Treat review, tests and CI as gates rather than optional cleanup.
- Split work into small ticket-to-PR loops.
- Preserve human approval at risk points such as deployment, secrets, destructive actions and public communication.
What Changed
The result is a delivery model where repetitive investigation and scaffolding can be automated while architectural decisions remain deliberate.