Stateful Agents on K8s: Redis is Your Bottleneck, Not the Vector DB
Agents are stateless. Their memory is not. Scaling the LLM reasoning loop is trivial compared to solving the transactional concurrency of agent memory on Kubernetes.
From the Front Lines of Tech
Sharing strategic insights and lessons from over 20 years of building scalable systems, leading high-performing teams, and navigating complex technology shifts.
Writing Pallas Kernels for JAX: Stepping Outside the XLA Safety Net
When XLA's heuristics fail for custom attention mechanisms, you can't just hope for a compiler update. Here is how you write Triton-like kernels directly in Python using JAX Pallas.
· StrategyThe Context Window ROI: Why RAG is a Tax on Reasoning
At $5 per million tokens with Gemini 2.5 Pro, the context window is no longer a scarcity. It is an asset class. It is time to rethink the true cost of RAG pipelines.
Optimizing LangGraph Cycles: Stopping the Infinite Loop
Preventing infinite recursion loops in reasoning chains with robust circuit breakers.
A2A Architectures: Tools are not just Functions (The Two-Phase Commit)
Why Agent-to-Agent (A2A) interactions and Side Effects require a 'Two-Phase Commit' for safety.
The Blackboard Architecture: Solving the Agent 'Phone Game'
Chains are brittle. We need a shared state object for robust multi-agent reasoning.