Two Patterns for Reducing LLM Costs in Data-Heavy RAG Apps (opens in new tab)

How we cut token usage significantly in an F1 telemetry analyzer by rethinking what goes into the context window — and when. When building RAG applications on top of structured data (databases, APIs, telemetry), the naive approach is to dump everything into the context and let the LLM figure it out. It works, but it's expensive and slow. After building F1 Analyst Pro — a chat interface for Formula 1 race analysis backed by FastF1 + Supabase + Claude — we refined two patterns that significantl...