
Use when designing AI-powered systems such as agents, LLM workflows, prompt pipelines, or human-AI collaboration tools. Applies system-level thinking to define agent responsibilities, orchestration patterns, safety guardrails, and evaluation strategies for reliable AI behavior in production applications.
Analyze a PR diff, map changed files to the exact affected test suites, run targeted tests, and report the full blast radius. Use when a PR is raised or when you want to validate the impact of recent changes without running the full test suite.
Use when defining product problems, shaping feature ideas, prioritizing roadmap decisions, or evaluating product-market fit. Applies outcome-driven product thinking inspired by Teresa Torres and Geoffrey Moore, focusing on customer discovery, user needs, value propositions, and strategic positioning before implementation.
Use when designing or reviewing the architecture of SaaS platforms, especially multi-tenant systems. Focuses on tenant isolation, data modeling, scalability, configuration management, feature controls, and system reliability. Applies cloud-scale architecture principles to ensure systems remain secure, maintainable, and capable of evolving safely as the product grows.
Use when evaluating or implementing software systems, reviewing architecture decisions, planning engineering work, or improving code quality. Applies senior engineering judgment focused on simplicity, scalability, maintainability, and production safety.
Use when analyzing complex systems where multiple components interact, such as SaaS platforms, AI agents, workflows, or organizational processes. Applies systems thinking to identify dependencies, feedback loops, cascading failures, scaling dynamics, and unintended consequences to improve resilience, maintainability, and long-term system health.
Use when designing user interfaces, workflows, or product interactions. Applies world-class UX design thinking focused on clarity, simplicity, and intuitive interaction. Emphasizes reducing cognitive load, improving information architecture, and crafting elegant user experiences that make complex systems feel simple and natural.
Use when reviewing feature quality, defining automated test coverage, analyzing edge cases, or assessing system reliability. Applies world-class SDET practices focused on correctness, observability, regression prevention, multi-tenant safety, and AI-agent failure handling across unit, integration, and end-to-end workflows.
Explains code with visual diagrams and analogies. Use when explaining how code works, teaching about a codebase, or when the user asks "how does this work?"-[2]