New Course — agenticai.varasrinivas.com

Production LLMOps
AI Application Lifecycle

The "day 2" discipline — evaluating, deploying, monitoring, upgrading, and governing LLM applications in production. Everything that happens after "it works on my laptop."

Domain anchor: Prior Authorization Determination Pipeline
Launch the interactive course →
32Modules
8Tracks
64Labs
66Ecosystem Links

Agentic AI Five-Pillar Curriculum

Context Eng.
Science
AI Agents
Applied
AI Platform
Infrastructure
LLMOps
Operations
AI-SDLC
Process

LLMOps is the operational discipline — it runs on the AI Platform, operates the Agents, and integrates into the AI-SDLC.
Target audience: ML engineers, SREs, DevOps engineers, and engineering managers running AI in production.

Ecosystem Cross-Reference Map

LLMOps ModuleOther CourseRelationship
M04–M07 Eval & TestingCE M29 Context A/B TestingLLMOps automates evals at scale; CE designs what to evaluate
M05 LLM-as-JudgePlatform M10 Prompt EvalSame technique, LLMOps focuses on production automation
M08–M11 DeploymentPlatform M11, AI-SDLC CI/CDLLMOps deploys the full app; Platform deploys prompts
M12–M15 MonitoringPlatform M28 ObservabilityApp-level monitoring vs Platform's infra-level
M13 Quality DriftCE M14 Context DecaySame concept — LLMOps detects it; CE prevents it
M16–M19 Feedback LoopsAgent M15 HITLLLMOps systematizes feedback; Agents implement HITL flows
M20–M23 Model LifecyclePlatform M05 Multi-ProviderLLMOps manages upgrades; Platform routes across providers
M24–M27 ReliabilityPlatform M07, M29App-level reliability vs Platform's infra-level
M28–M30 GovernancePlatform M16–M19 CostApp-level optimization vs org-level budgets
M31 CapstoneAll capstonesLLMOps capstone operates the prior-authorization pipeline others build