Research · Runs
Inspect the runs
Every run behind Same Model, Different Harness: 7 models in 5 agent harnesses on Datacurve’s DeepSWE v1.1, two runs per task. Filter to a pairing or a task, then open a run to read what the agent did, step by step.
We raised our Series A. Here is what we are building next. Read more→We raised our Series A.
Here is what we are building next.Our modernization work with CMS, 18 million lines of Medicare claims code made readable →Our modernization work with CMS,
18 million lines of Medicare claims code made readableWe raised our Series A. Here is what we are building next. Read more→We raised our Series A.
Here is what we are building next.
Here is what we are building next.Our modernization work with CMS, 18 million lines of Medicare claims code made readable →Our modernization work with CMS,
18 million lines of Medicare claims code made readableWe raised our Series A. Here is what we are building next. Read more→We raised our Series A.
Here is what we are building next.