01PROPOSE
Write a falsifiable claim
An agent reads the tables and proposes one. Near-duplicates never enter the tree.
BAYESIAN SURPRISE IN MONTE CARLO SEARCH TREES
Agentic AI autoresearch grounded in your datasets.
It proposes the hypothesis, writes and runs the experiment, then searches for external data that could challenge the result.
THE SEARCH LOOP
Test a claim from several evidence paths.
02SEPARATE
Answer it twice, blind
Two agents answer at once, each prepared without the other's evidence.
Literatureno tables in its workspace
Experimentno literature verdict
03CHALLENGE
Spend effort on surprise
Where those answers diverge, a fourth agent searches for a compatible external dataset and tests the claim again.
04UPDATE
Grow the search tree
MCTS scores the branch and picks where the next experiment is worth the compute.
LIVE EVIDENCE
The lead view is selected by a fixed rule, not editorially.
Loading published runs…