Agentic DevOps Engineer

Retrieval-Augmented Generation (RAG) is an AI architecture pattern that combines a language model with a knowledge retrieval system. Instead of relying solely on the model's training data, RAG retrieves relevant documents from a knowledge base and includes them in the prompt, grounding the AI's responses in specific, verifiable information. RAG reduces hallucinations by giving the model factual context to work with. It's the most popular enterprise AI pattern in 2026 because it allows organizations to use their proprietary data with general-purpose language models without fine-tuning. The economics of RAG involve balancing retrieval costs (vector database queries, embedding generation) against the cost of hallucination and the alternative cost of fine-tuning. For most enterprise use cases, RAG is significantly cheaper than fine-tuning while providing better accuracy on domain-specific questions.

A Large Language Model is a type of artificial intelligence trained on vast amounts of text data to understand and generate human language. LLMs like GPT-4, Claude, Gemini, and Llama power chatbots, code assistants, content generation, and enterprise AI applications. LLMs work by predicting the next token (word or word-piece) in a sequence. They're trained on billions of parameters using transformer architecture. The 'large' in LLM refers to both the training data (often trillions of tokens) and the model size (billions of parameters). The economics of LLMs are unique: unlike traditional software with near-zero marginal cost, LLMs have significant variable costs that scale with usage. Every query costs compute. This creates what Richard Ewing calls the Cost of Predictivity — as you demand higher accuracy, costs scale exponentially.

AI inference is the process of running a trained model to generate predictions or outputs from new input data. Unlike training (which is done once), inference happens every time a user interacts with an AI feature — every chatbot response, every code suggestion, every image generation. Inference cost is the dominant variable cost in AI features. Training GPT-4 cost an estimated $100M, but inference costs across all users dwarf that number. Each inference call consumes GPU compute proportional to model size and input/output length. Inference optimization is a critical engineering discipline: model quantization (reducing precision from 32-bit to 8-bit or 4-bit), batching (processing multiple requests simultaneously), caching (storing common responses), and distillation (creating smaller student models from larger teacher models). For product leaders, inference cost is the unit cost that determines whether your AI feature has positive or negative unit economics. Richard Ewing's AUEB tool calculates Cost of Predictivity — the true per-query cost including inference, retrieval, verification, and error handling.

DORA metrics are four key software delivery performance metrics identified by the DevOps Research and Assessment (DORA) team at Google. They are the industry standard for measuring engineering team effectiveness: 1. **Deployment Frequency**: How often code is deployed to production. Elite teams deploy on-demand, multiple times per day. 2. **Lead Time for Changes**: Time from code commit to production deployment. Elite teams achieve less than one hour. 3. **Change Failure Rate**: Percentage of deployments that cause failures requiring remediation. Elite teams maintain 0-15%. 4. **Mean Time to Recovery (MTTR)**: How quickly a team can restore service after an incident. Elite teams recover in less than one hour. These metrics are backed by years of research across thousands of organizations worldwide and are validated as predictors of both software delivery performance and organizational performance.

Orchestration Debt is an emerging form of AI technical debt (2026) created when autonomous AI agents interact with multiple enterprise systems, creating complex dependency chains that are difficult to monitor, debug, and maintain. As organizations deploy agentic AI workflows where agents call other agents, access databases, invoke APIs, and make decisions autonomously, the orchestration layer between these components accumulates debt through: undocumented dependencies, brittle error handling, cascading failure modes, and untested interaction patterns. Orchestration debt is uniquely dangerous because it is invisible — each individual agent may work correctly, but the interactions between agents produce emergent behaviors that no single team designed or tested.