Visual readers / Agents · Cloud · Inference
Nine visual field guides connect autoscaling, cloud economics, agent authority, workload behavior and accelerator execution. Follow a short automatic sequence, then read the example and its assumptions—no controls to configure.
Choose a question
A traffic spike does not create a node directly. Follow one microservice through the control loops, then inspect the requests, policies and readiness conditions between a recommendation and usable capacity.
Cloud cost optimization
An impressive percentage needs a reconciled bill. Follow five explicit assumptions to see where the modeled $1.6M monthly reduction comes from—without adding overlapping discounts twice.
Agent security
A sandbox contains execution. A policy decides which action is authorized. Follow the boundaries to see why those are different responsibilities.
Kubernetes workloads
A controller wants replicas. A scheduler needs capacity. A Service needs ready endpoints. A disruption budget answers a different question again.
Inference engines
Start with fit within the total modeling budget. Then separate the cost of moving data from doing arithmetic. A low-precision label or a peak specification cannot answer either question on its own.
Cloud decisions
Normalize the workload and quote boundary first. Then inspect the modeled line items without pretending that cost alone selects an architecture.
Kernel development
A faster arithmetic unit cannot remove a data-movement bottleneck. Follow the data and see what tiling can—and cannot—buy.
A scheduled GPU is not an unlimited token budget. Allocate the memory explicitly, then distinguish an arithmetic capacity limit from a safe serving policy.
Compilers & accelerators
Follow the programming model into the compiler and device. The useful comparison is who controls each boundary—not which unrelated peak number wins a chart.
Engineering notes
Real client engagements and the engineering behind them.
A real operations team turned an AI agent pilot into bounded work using sandboxing, prompt-injection defenses and explicit tool authorization.
A real order platform follows Pods, probes, rollout capacity and PodDisruptionBudgets to shorten release recovery without inventing uptime guarantees.
A real B200 deployment links KV cache, batching and vLLM vs TensorRT-LLM to cost per useful response, with explicit latency and quality assumptions.
A real SaaS migration compares AWS, Azure and Google Cloud through identity, egress and operating cost, with a transparent payback example.
A real forecasting deadline made CUDA matrix multiplication a business decision. Learn shared-memory tiling, correctness and application-level limits.
A real ranking service uses JAX softmax to study kernel fusion, numerical stability and GPU memory traffic, with a bounded end-to-end latency model.
A real support platform links Kubernetes GPU scheduling and autoscaling to inference cost, model readiness and service-level objectives.
A real forecasting company compares JAX, CUDA, GPUs and TPUs at the right layers, using compilation, transfer and run-time costs—not brand rankings.
A useful next conversation
A system, a delivery bottleneck, or an engineering opportunity. Tell me what you are building and where you want to go.
Let’s talkTechnical glossary: definitions, connected ideas and further reading.
Optional analytics off. Contact works either way.