•case study•12 min
Scaling RAG to 10 Million Queries
How we 10x'd throughput while cutting costs by 80%. Deep dive into optimization strategies for production RAG systems.
ragscalingoptimization
Research & Writing
Thoughts on AI operations, production ML systems, and the gap between research and reality.
•case study•15 min
Building Agents That Don't Suck
Lessons from shipping autonomous AI to production with 94% task success rate.
agentsproductionai
•blog•5 min
Speed Is the Strategy
In AI, the half-life of competitive advantage is measured in weeks, not years.
aistrategyshipping
•blog•8 min
RAG in Production: What They Don't Tell You
The gap between RAG demos and production RAG is wider than you think.
ragproductionllm
•blog•4 min
What Even Is AI Ops?
A new role for a new era of software.
careerai-opsrole