All articles
BLOG / TOPIC
AI platform engineering
An AI platform team owns the shared plumbing that every AI product team would otherwise rebuild: gateways, serving, evaluation and release pipelines, and observability. These articles explain what each piece does and how to decide.
4 articles on this topic
Ordered from foundations to advanced, newest first within each level.
- API or Local Models: Where the Cost Break-Even SitsWhen does running a model yourself beat paying for an API? A total-cost framework, an illustrative break-even calculation and the non-cost factors that decide.Intermediate 9 min readLast reviewed 2026-10-11
- LLM Observability: What to Trace and WhyWhat to trace and log in a production LLM app: prompts, retrieved context, tool calls, tokens, cost and latency, with sampling, privacy and alerting guidance.Intermediate 9 min readLast reviewed 2026-10-11
- What an AI Platform Engineer Actually OwnsWhat an AI platform team builds and runs: gateway, serving, evaluation pipelines, observability, cost and security, and where product teams take over.Intermediate 9 min readLast reviewed 2026-10-11
- LLM Gateways: What They Do and How to Choose OneWhat an LLM gateway does, when you need one and how to choose: authentication, routing, budgets, caching, logging and policy, with a vendor-neutral scorecard.Advanced 9 min readLast reviewed 2026-10-11