Enables an agent to submit a task and two options and receive a recommendation of the better option with a calibrated confidence percentage and a reason, to support decision-making.
Provides local, read-only recommendations for reasoning effort, retry or escalation guidance, and integration boundaries, enabling compatible desktop apps to suggest effort levels without modifying the active conversation.
Enables coding agents to submit their original request, proposed plan items, and observed repository conventions for per-item necessity scoring before making edits. It returns advisory keep, simplify, or review recommendations with reasons and evidence, without blocking or modifying the plan.
Enables agents to evaluate whether a product-adoption message is worth sending by applying a fixed, evidence-based rubric to a draft, recipient context, evidence, and the agent's own assessment, returning a send, revise, or hold recommendation with a score and reasons.