Agent Tool Scoring

how to access alc open the agent tool scoring page by clicking tools in the main toolbar at the top of alc, then choosing agent tool scoring from the menu migrator open the estimator dashboard , click the center report dropdown and select agent scoring overview ai agent tooling has historically centered almost exclusively on api based tools as a result, using ai agents to automate interactions with legacy systems where apis aren't available has been difficult by using the ai agent as the orchestration layer and exposing your existing rpa flows (or the components within them) as the available tools, agents can automate tasks in systems that have no readily available api — backed by automation that has already been vetted and relied upon in production the agent tool scoring page analyzes and grades each pad component in your currently selected estimalc environment to identify the strongest candidates to become agent tools what gets scored blueprint looks for 3 types of components flows — the entire automation / call tree (a "main") the root process plus everything it calls subflow — a singular subflow within a pad flow that the author deliberately defined subtree — any node taken together with all its downstream descendants blueprint treats every node as if it's the root of a candidate subtree understanding the score each component receives a single grade, shown as a percentage, that reflects how ready it is to become an agent tool higher scores indicate components that are easier and safer to expose as a tool — generally smaller, self contained units with explicit inputs, limited branching, and few hidden dependencies click any score to open a side panel with the full breakdown of the individual metrics that contributed to the grade the factors considered include the number of actions, the number of arguments, unique applications touched, decision complexity (ifs, switches, and loops), undeclared variables, exception handling, and any hard coded sensitive values not every factor is weighted equally; the metrics that most affect a component's suitability as a tool contribute the most to the overall grade most of a component's score is static and are recalculated only when you modify the underlying process and re import it the exception is runtime data when include runtime data is enabled, blueprint updates those metrics on a semi real time basis as executions happen, so the portion of the score derived from runtime data can change without a re import features component filter — use the center dropdown to limit results to specific component types (flow, subflow, or subtree) include runtime data (alc only) — when enabled, runtime data for pad flows imported to alc is factored into the score this requires msft 365 authentication and enable dataverse synchronization to be configured if those settings aren't configured, leave this toggle off filters — filter the table by the value in any of the columns listed below table glossary column header description score % displays the grade for the component as a percentage click the value to open a side panel with a breakdown of every metric considered in the grade component name displays the name and type of the component subtrees appear as a clickable link that lists all downstream components as a flat list parent flow name displays the parent flow the component originated from