Pat Simmons sets up separate workspaces for Grok Bot, Dots and Muse, then gives each agent comparable instructions for a fictional coffee businessEvaluation is the systematic assessment of a system's behaviour or results against explicit criteria.. The task spans customer emails, CRM updates, project tracking and website changes, providing a concrete way to inspect how the tools handle connected work.
The review also tests a shopping errand and travel planningA personal AI agent uses a person's authorized goals, preferences, routines, context, and tools to provide continuing individualized assistance., and compares onboarding, account connectionsApplication integration connects software systems so data and actions can move through one useful workflow., memory and user approval flows. Pat Simmons shows raw outcomes and failuresAgent completion verification checks evidence that an agent achieved the requested outcome rather than merely producing intermediate work. rather than assuming that all three products can safely complete every delegated task.
Pat Simmons closes with a situational comparison of the tools' capabilities and limitations. The results describe his particular tests and setup, not a universal ranking or an assurance that an agent should receive unrestricted access to real business accounts.
Watch on YouTube




