A Faster Librarian

Ampcode's Librarian AI agent is now approximately three times faster and 43% cheaper after switching to OpenAI's GPT-5.5 model with websocket mode, reducing average search latency from 237 seconds to 81 seconds and cost from $1.21 to $0.69 while maintaining quality.

The Librarian https://ampcode.com/news/librarian is now ~3x faster and 43% cheaper, with the same quality. It now runs on GPT-5.5 no reasoning with websocket mode https://ampcode.com/news/faster-deep-rush and an updated system prompt that encourages more parallel exploration. The Librarian fires ~8 tool calls in parallel per turn, up from ~3 with Sonnet, and wraps up a search in ~5 turns instead of ~15. In our internal eval, about a quarter of that speedup comes from OpenAI's websocket mode and the rest from switching to GPT-5.5 with no reasoning: | Sonnet-4.6 medium | GPT-5.5 none | | |---|---|---| | Latency mean | 237s | 81s 2.9x faster | | ↳ gain from websocket | — | ~1.3x | | ↳ gain from model | — | ~2.2x | | Quality F1, mean | 0.47 | 0.48 | | Average cost | $1.21 | $0.69 | Here's a comparison: How does Kubernetes' HorizontalPodAutoscaler handle missing pod metrics when scaling down — does it assume missing pods are at 100% of their resource requests, or 100% of the target utilization? Cite the function and logic in the source. Sonnet 4.6 left took 2 minutes and cost $1.08, while GPT-5.5 right took 40 seconds and cost just $0.47.