Scale Intelligence■ Docs
Docs / Registers / tool si.read.policy_replay

tool si.read.policy_replay.

A policy row and its version, a strategy and a window (`PolicyReplayInput`): what the policy would have chosen at every logged decision against what was chosen, and the effects that followed (`PolicyReplay`).

Figure 1si.read.policy_replayspecified
AGENT'S HOSTClaude Code orany MCP clientMCP SERVERsi.read.policy_replaytasks, appsCORE: READinput PolicyReplayInputCARDbody PolicyReplayThe host draws the card from ui://scale-intelligence/cards/PolicyReplay.flows forwardthe result
Over MCP, si.read.policy_replay takes PolicyReplayInput and returns a card whose body is PolicyReplay.

what the policy would have chosen at every logged decision against what was chosen, and the effects that followed (PolicyReplay). The call needs the read grant at the strategy rung.

result
a card whose body is PolicyReplay
read-only
yes
destructive
no
card address
ui://scale-intelligence/cards/PolicyReplay
fieldtyperequirednote
policyPolicyyes
strategyidyes
windowWindowno

Claims#

claimstateroute or tool
The MCP server declares si.read.policy_replay at contract 0476e35e6e275db5.targetsi.read.policy_replay