News
Updates from Jean Technologies.
Matching the Internet of Agents
Project Deal showed AI agents can transact for us. When everyone has 100 agents acting in their name, finding the right ones and verifying the ones we find becomes the load-bearing infrastructure.
We competed at the AGI House Internet of Agents Build Day on the simulated and RL track. The premise (100 agents per person) reframes our matching thesis: same primitive, harder substrate, and a trust gap that did not exist for human matching.
Emotion Vectors and the Future of Matching
Anthropic just published landmark research showing that LLMs maintain abstract, causally operative representations of emotion. This is something we have been thinking about for a long time, and it changes how we should build matching systems.
Why General-Purpose Embeddings Fail at Human Matching
Standard embedding models are trained on text similarity. But when the goal is predicting compatibility between people, text similarity is the wrong objective entirely.
Local Drift-Adapters
A single global adapter fakes an embedding-model upgrade for a fraction of the cost, but its uniform-drift assumption breaks on real corpora. Local drift-aware adapters close most of the gap.
Introducing the Embedding Adapter
Switching embedding providers has historically meant re-encoding your entire vector corpus. Today we are releasing infrastructure that eliminates that requirement.
Jean Technologies
We started Jean Technologies to solve a problem we kept seeing across industries: platforms that match people to people, or people to opportunities, using infrastructure designed for document search.
General Personal Embeddings
An exploration of how deep representation learning can be applied to people, and why the logical endpoint is trusted infrastructure for personal embeddings.