tip/22so simple
Cache your long system prompt.
If every API call repeats the same long instructions or document, turn on prompt caching. Repeated input gets much cheaper and faster.
Claude API · Build with LLM APIs22 / 32
teechmeai/tips30-second
30-second
wins.save these!
Small habits that make AI noticeably better. Read one, use it today. Prompts are highlighted, so copy and go.
32 tips · 8 topics · 0 fluff
start here ↓
tip/23
Stream long answers.
Stream responses in your app. Users see text immediately and you avoid HTTP timeouts on long generations.
Any LLM API · Build with LLM APIs23 / 32
tip/24pro move
Keep 20 test questions.
Before changing a prompt or model in production, rerun a small fixed set of real questions. Vibes are not a test suite.
Any LLM API · Build with LLM APIs24 / 32
tip/25save this!
Overlap your chunks.
In RAG, split documents on headings or paragraphs with a little overlap, so an answer that spans a boundary isn't lost.
RAG · Build with LLM APIs25 / 32