Latest Posts
Notes on agents, infrastructure, and everything that broke along the way.
Agent pipelines, LLM integration, and automation built to run on hardware you control — not a subscription you rent. From inference serving to full deployment automation.
Practical AI engineering — agents, inference infrastructure, and the automation that keeps it running.
Autonomous and semi-autonomous agents wired into real tools and real workflows — not just chat demos.
agentsWiring language models into existing systems: retrieval, tool-use, structured output, and evaluation.
llmDeployment, monitoring, and recovery automated end to end — infrastructure that repairs itself before you notice.
automationLocal model serving on your own hardware — full control over data, cost, and latency, with no vendor lock-in.
inferenceArchitecture that scales from a single box to a full multi-node lab, designed for the failure modes that actually happen.
architectureMonitoring, alerting, and incident response built in from day one — not bolted on after the first outage.
reliabilityThe tools underneath the agents.
Notes on agents, infrastructure, and everything that broke along the way.