PM
AboutExperienceProjectsPlaybookBlogResume
Back to Home

Engineering Playbook

Opinionated guides on building production ML systems. Not tutorials—lessons learned from shipping AI at scale.

Architecture12 min

Production LLM Architecture Patterns

How I design LLM pipelines that scale—preprocessing, chunking strategies, prompt engineering, and system architecture that survives production.

LLM Patterns8 min

Structured Outputs > Prompting: How I Make LLMs Deterministic

Moving beyond prompt engineering to contract-first design with Pydantic schemas, validation layers, and structured outputs.

RetrievalComing Soon

Embeddings in the Real World: Two-Tower Ranking and When Cosine Fails

From cosine similarity to production retrieval—calibration, two-tower models, and evaluation beyond offline metrics.

MLOpsComing Soon

Evaluation and Feedback Loops for AI Products

From offline metrics to online learning—drift monitoring, regression tests, A/B testing, and continuous evaluation pipelines.

OptimizationComing Soon

Latency/Cost Playbook for LLM Apps

What I optimize first when building LLM applications—caching strategies, model selection, prompt compression, and batching.

RetrievalComing Soon

GraphRAG for Complex Document Understanding

When vanilla RAG fails—using knowledge graphs for legal documents, contracts, and complex hierarchical content.

© 2026 Patrick McBride. Built with AI.