·
9 min
Prompt Caching: Cutting LLM Latency and Cost
A practical guide to prompt caching with the Claude API: cache_control, cache-hit verification, and the mistakes that quietly break it.
#Llm
4 Articles
·
10 min
How to Stream LLM Responses in a Web App
Learn how to stream LLM response output in a web app with SSE, EventSource, fetch ReadableStream, and a PHP/Laravel server example.
·
11 min
Getting Reliable LLM Structured Output JSON in PHP
Stop parsing broken LLM JSON. A practical PHP/Laravel guide to reliable structured output using tool calling, schema validation, and retries.
·
11 min
How to Evaluate LLM Output So You Can Ship and Iterate Safely
A practical guide to evaluate LLM output: golden datasets, deterministic checks, LLM-as-judge, human review, and regression testing.