ModelRefs / AI Architecture Guides
AI Architecture Guides
Design AI systems, integration patterns, data flows, and deployment architectures.
Overview
This section holds 2 decision guides, each with a step-by-step framework, the trade-offs it forces, and the sources behind it.
AI Architecture Guides
Design AI systems, integration patterns, data flows, and deployment architectures.
How to choose between fine-tuning and RAG
A decision framework for choosing retrieval, fine-tuning, or a hybrid approach based on knowledge freshness, behavior adaptation, data, evaluation, cost, maintenance, and risk.
Level: intermediate · About 10 to read
How to choose between a managed API and self-hosted models
A decision framework for the deployment path itself — managed API, self-hosted open-weight models, or a mix — based on data handling, regional constraints, operational ownership, cost shape, and exit options rather than a universal recommendation.
Level: intermediate · About 9 to read
Other decision-guide sections
- Model Selection Guides — Choose models by use case, capability, constraints, and implementation trade-offs.
- Provider Selection Guides — Compare provider options, deployment paths, APIs, pricing factors, and operational constraints.
- Benchmark Interpretation Guides — Understand benchmark results, limitations, evaluation context, and practical relevance.
- Workflow Implementation Guides — Plan and implement AI workflows such as RAG, agents, fine-tuning, and evaluation.
- Governance Guides — Apply governance, risk, review, and monitoring practices to AI implementation decisions.
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to AI Architecture Guides.