YottaDynamics Technical Notes
Infrastructure, AI agents, and platform engineering — written for engineers building production systems.
Get Started Hosting Your Own LLMs Using Ollama: Your Private AI Playground
Ollama is one of the fastest ways to move from cloud API dependency to local model serving on your own machine. This guide covers installation, first-run commands, model selection, Open WebUI, Modelfiles, and basic API usage.
Observability for AI Agents: Logs, Traces, and Metrics That Actually Tell You Something
Monitoring an agent is not the same as monitoring a service. The question shifts from whether it is running to whether it is reasoning correctly — and that requires a different observability stack built around structured traces, quality metrics, and cost attribution.
Why Agents Fail in Production (And How to Catch It Before It Reaches Your Users)
Non-deterministic systems require evaluation strategies that traditional QA cannot provide. Closing the gap requires a golden dataset, trajectory analysis, an LLM-as-judge pipeline, and a feedback loop that runs before every deployment.
How Memory Works in AI Agents: Turning Stateless LLMs into Persistent, Learning Systems
LLMs are stateless by design. Memory is the external infrastructure that turns them into agents that learn from experience, remember preferences, and actually improve over time. Here’s how it works — technically.
A Deep Dive into Retrieval-Augmented Generation (RAG)
RAG fixes the core problems with pure LLMs — hallucination, stale knowledge, private data — by making retrieval a first-class citizen. Here’s the full technical picture: vector search, hybrid retrieval, GraphRAG, agentic patterns, and what a production stack actually looks like in 2026.
The Technical Blueprint for AI Speed: Markdown vs. RAG
The storage format you choose for AI knowledge directly shapes your system’s latency, token density, and semantic clarity. A pragmatic breakdown of when to use raw Markdown, when to build a RAG pipeline, and why the best production systems use both.
AI Agent Architecture: Memory, Tools, Orchestration, and Production
Most ‘my agent broke’ investigations don’t end at the model. They end in memory design, tool scope, orchestration logic, or missing observability. This post covers the plumbing that actually determines whether an agent works in production.
Hosting Local LLMs on Kubernetes: A Complete Enterprise Architecture Guide
A deep-dive into every layer of a production-grade, fully open-source stack for self-hosting large language models — from the API gateway to the GPU compute plane.
What Is an AI Agent? A Practical Guide for Builders
The term ‘AI agent’ gets applied to everything from a ChatGPT thread with a button to systems that autonomously manage deployments. That imprecision directly shapes the architectures you choose and the failure modes you inherit.
Claude Code in the Terminal: The Deep-Dive
Most teams use Claude Code like a smart autocomplete. The teams getting real leverage treat it as an engineering platform — with CLAUDE.md, permissions, hooks, sub-agents, skills, and CI/CD integration designed in from the start.