Tamara Tran
Tamara Tran is a builder at Jev, TypeSafe AI's decision model, where she works on agent context management and compaction. She is best known for creating fast-jev-compaction, an open-source Claude Code plugin that scores individual tool outputs and discards irrelevant entries instead of summarizing them, preserving original tool outputs verbatim in the context window. Her compaction demo, which applies Jev's scoring model to prune agent context per tool call, reportedly reduced a Claude session from nearly one million tokens to 86K in approximately one second.
“Tamara Tran's compaction demo did 3.6M views: score every tool call in a Claude session, drop the irrelevant ones.”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.