Teahose.
SIGN IN
NEW HERE — WHAT TEAHOSE DOES
We read the entire AI & tech firehose — so you don't have to.
PODPodcastsAll-In, No Priors, Acquired…
NEWNewslettersStratechery, Newcomer…
PAPPapersPhysical AI research
PHProduct Huntdaily launches
VCInvestor ScoutSequoia, a16z, Benchmark…
CLAUDE DISTILLS →
7 reads, 30 sec each — free, 6 AM ET.
+ a live graph of the companies, people & themes underneath.
HOME/PEOPLE/TAMARA TRAN
// PERSON

Tamara Tran

ROLE BUILDERAT JEVMENTIONS 1LAST SEEN SEPTEMBER 20, 2026
// BIO

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.

Discussed in
// RECENT MENTIONS
// SIGNALS
1 SIGNAL
01
mention·The AI Corner·SEPTEMBER 20, 2026

“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.