#benchmarking
2 entries
projects · March 2026
sysml-bench
An evaluation harness that measures whether giving a tool-augmented LLM more tools helps it answer questions about a SysML v2 model: typed tasks scored per field against published schemas, four tool sets called through a command line, public corpora of several sizes, and a pre-registered replication on an independent corpus.
writing · March 2026
Meeting Notes RAG
A RAG pipeline for searching customer meeting notes: embedding, vector search, and synthesis without a SaaS intermediary.