Check Understanding
checkValidate your understanding against human intent and record alignment checks, with integrated Bayesian decision trails for tracking confidence and evidence.
Instructions
[MID-SESSION — safe any time; for alignment, before risky decisions] Use when the user asks to validate understanding, verify alignment, or check if their interpretation matches the human's intent.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| goal | No | The goal or decision question you're checking alignment on. Required for alignment checks; optional when recording a pure decision trail (prior/posterior/evidence). | |
| understanding | No | Alias for goal — use when saying 'check my understanding: X'. Provide either goal or understanding. | |
| confidence | No | How confident you are. Defaults to medium. | medium |
| assumptions | No | Key assumptions you're making. | |
| human_correction | No | After human responds: what they actually wanted (or 'confirmed'). | |
| delta | No | The gap between your understanding and reality (or 'none'). | |
| project | No | auto | |
| prior | No | Initial probability estimate (0-1). Start of Bayesian decision trail. | |
| evidence | No | Evidence collected since prior. Each entry shifts probability. | |
| posterior | No | Updated probability after considering evidence (0-1). | |
| outcome | No | Final decision result: 'confirmed', 'rejected', 'partial', or free text. Triggers decision trail persistence. | |
| decision_id | No | Link multiple check calls to the same decision. Auto-generated if not provided. |