FROGENT / capability index

Eleven scientific tasks. Eleven evidence-bearing pages.

Open the task you need. Each page explains the scientific question, the agent action, its inputs and outputs, the source figure, and the boundary of the evidence.

Shared context

Every capability reads from and writes to the same campaign record.

Human checkpoints

Experts can inspect evidence, constraints, rankings, failures, and artifacts before the next decision.

Evidence boundaries

Predictions and generated proposals stay distinct from experimental or clinical confirmation.