An agent-skills workflow you can actually verify
Try one skill on a small task, measure its context cost, and keep a before-and-after evaluation. A free practical lesson for engineers.
Agent SkillsClaude CodeEvals
Guides
AI engineering guides
Step-by-step how-tos for shipping production AI — building RAG pipelines, evaluating LLMs, fine-tuning, serving open models, and monitoring what runs. Written from doing the work, not reading about it.
How to build a RAG pipeline
An end-to-end walkthrough of a production RAG system: ingestion, chunking, embeddings, vector store, retrieval, reranking, generation, and the eval loop.
RAGAI EngineeringRetrieval
How to chunk documents for RAG
A practitioner's guide to fixed-size, recursive, semantic, and structural chunking — with the size, overlap, and metadata tradeoffs that move retrieval quality.
RAGChunkingAI Engineering
How to deploy vLLM in production
A practitioner's guide to serving open-source LLMs with vLLM: batching, KV cache, quantization, multi-GPU, autoscaling, and metrics.
vLLMInferenceInfrastructure
How to evaluate LLMs
A practitioner's guide to LLM evaluation: golden datasets, LLM-as-judge, deterministic metrics, and regression gating in CI.
LLM EvalsAI EngineeringTesting
How to fine-tune an LLM
A practitioner's guide to deciding when to fine-tune, using LoRA and QLoRA, preparing data, evaluating results, and serving adapters in production.
Fine-tuningLoRAAI Engineering
How to monitor LLM apps in production
A practitioner's guide to tracing, cost and latency metrics, online quality checks, drift detection, and feedback loops for production LLM systems.
ObservabilityMonitoringAI Engineering
How to reduce LLM hallucinations
Practical techniques to ground, constrain, and verify LLM output so it stops inventing facts in production.
HallucinationGuardrailsAI Engineering