← all posts

AI Ops

Running AI systems in production

AI Agent Memory: Sessions, Long-Term State, and Retrieval

Tutorials AI Ops

Design AI agent memory without a data swamp: session state, durable facts, retrieval, provenance, conflicts, privacy, deletion, and production evaluation.

MCP Security: OAuth, Tool Permissions, and Prompt Injection

Tutorials AI Ops

Secure remote and local MCP servers with OAuth audience binding, least-privilege tools, prompt injection defenses, sandboxing, audit logs, and tests.

Production LLM Stack: Routing, Evals, Cost, Reliability

Tutorials AI Ops

A practical production LLM stack: request contracts, model routing, tools, validation, observability, evals, cost controls, fallbacks, and safe rollouts.

Testing AI Agents: How to Know Your Agent Actually Works

AI Ops

A practical guide to testing AI agents: unit/integration/e2e tests, eval frameworks (DeepEval 4.0, RAGAS, Promptfoo, Braintrust), metrics, CI/CD pipeline. With code examples.

Context Engineering vs RAG: When to Use Which

AI Ops

A deep comparison of context engineering and RAG: when long context replaces retrieval, when you actually need RAG, a decision framework, and the modern 2026 stack.

AI Agents: The Complete Guide - What They Are, How to Build Them, Where to Use Them

AI Ops

A complete guide to AI agents: architecture, frameworks (LangGraph, CrewAI, OpenAI Agents SDK, Google ADK, Pydantic AI, MCP), practical use cases, and a hands-on tutorial.

Prompt Library Template: A 5-Part Framework

Tutorials AI Ops

A 5-component prompt template for building a reusable library. Structure, examples for different tasks, plus organization and versioning of a prompt library.

LLM Cost Optimization: Measure Cost per Successful Task

Cases & Practice AI Ops

Reduce LLM spend without hiding quality loss: attribute costs by task, remove waste, set output budgets, test smaller models, use caching safely, and control retries.

Kronos Agent OS: a self-hosted runtime for durable AI agents

Engineering AI Ops

An evidence-based tour of KAOS v0.3.0: durable turns, layered memory, MCP tools, governance, behavior evals, portable agent state, and safe defaults.

Human-in-the-Loop for AI: Approval Gates That Work

Tutorials AI Ops

Design human oversight for AI actions with risk tiers, approval state machines, calibrated routing signals, reviewer UX, queue SLAs, audit logs, and release metrics.

Prompt A/B Testing: a scientific approach to improving AI response quality

Tutorials AI Ops

Methodology for A/B testing prompts: quality metrics, statistical significance, tools (Langfuse, DeepEval). Step-by-step guide from hypothesis to production decision.

Prompt Engineering in Production: Versions, Evals, Rollbacks

Tutorials AI Ops

A production prompt-management workflow for versioning, dataset evals, canary rollouts, trace-linked metrics, caching, and safe rollback with Langfuse.

Multi-Agent Architecture Patterns: When One AI Isn't Enough

Tutorials AI Ops

Multi-agent system architecture patterns for production: Sequential Pipeline, Parallel Fan-Out, Classifier+Router orchestration, task routing, agent specialization with code examples.

LLM-as-Judge: Build a Calibrated Quality Gate

Tutorials AI Ops

Design an LLM judge with narrow rubrics, human calibration, deterministic checks, bias tests, CI gates, production sampling, and safe handling of untrusted outputs.