HumanAgent Interface
Take Action
Action Type
*
:
Discrete simulator step type. The environment enforces scientific prerequisites between steps, so actions should follow a valid pipeline order.
Input Targets:
Optional references to prior samples, outputs, or artifacts that this step consumes.
Method:
Optional named tool or protocol (for example 'Seurat' or 'CellRanger'). Prefer methods compatible with the current modality and available tool list because tool choice can change runtime, cost, and scientific fit.
Parameters:
Action-specific settings such as comparison labels, perturbation targets, or analysis options. Use only parameters that materially change the scientific step.
Expected Output Type:
Optional expected artifact or summary that should result from the step, such as a count matrix, QC report, DE table, or validation result.
Justification:
Short scientific rationale explaining why this is the right next step in the current environment state.
Invoked Subagent:
Sub-agent to delegate to, if any
Tool Call Spec:
Optional structured tool invocation payload when the action needs a more explicit tool execution plan.
Confidence:
Agent confidence in this step
Step
Reset Environment
Get State
Current State
Status:
Not initialized
Episode ID:
-
Step Count:
0
State Observer
Current Observation
No observation yet
Action History
No actions taken yet