AI-Native Engineering Leader · 25 years in SDLC · Building production-grade agent systems with LangGraph, CrewAI, and circuit breakers · ex-Microsoft · WBD
Engineering leader with 25 years building CI/CD platforms, developer experience tooling, and cloud infrastructure at Warner Bros. Discovery, Microsoft, and Nordstrom. Currently building production-grade AI agent systems — circuit breakers, model routing, cost boundaries, and reliability patterns for LLM agent loops. Author of ai-loopguard, an open-source circuit breaker for agent loops.
Markdown supported · ⌘↵ to post
Kartik N V J K
The integration realism point is what separates useful evals from academic exercises. An agent that passes every unit test in a sandbox can still fail the moment it touches a real API with rate limits and stale data. The hardest part is not writing the eval, it is building a test environment that is realistic enough to matter. What is your approach to mocking external dependencies?