Blog
Notes from building queue-driven and AI-native backends at scale - distributed systems, Kubernetes, performance, and the failures worth writing down.
10 min read
Why Single-Agent AI Hits a Wall - and How Multi-Agent Orchestration Fixes It
Single agents monologue, teams converse - why complex work needs planners, schedulers, typed messaging and a message bus, not a bigger model.
Multi-Agent SystemsAI AgentsOrchestrationLLMDistributed Systems
12 min read
Vector Search Is a Strategy, Not an Architecture
Why cosine similarity can't answer causal, temporal, or ordered questions - and how Karpathy's LLM Wiki reframes retrieval as write-time compilation, seen from building a seven-strategy retriever.
RAGVector SearchKnowledge GraphsLLMRetrieval
9 min read
Cutting Kubernetes Cluster RAM by 50%: What Actually Caused the Bloat
How a responsibility split halved a Kubernetes cluster's RAM - why long-running workers pay for imports they never use, and how to find the same bloat in yours.
KubernetesPythonDistributed SystemsPerformanceCelery