Druid AI Co-founder Pleșea: The Root of Enterprise Agent Misunderstanding Is Ontological
Using a 2011 brick negotiation study as an example, Druid AI co-founder Pleșea explains the semantic roots of why enterprise agents fail to understand each other; CEO Kim points out that routing patterns cannot combine deterministic writes with flexible reasoning, meaning business system writes still require existing structured channels.
A seller describes bricks in one specification, while another buyer searches using different terminology; both sides use different words but refer to the same batch of bricks. For two programs to reach a transaction, they must first agree on what constitutes a brick. Andreea Pleșea, co-founder of Druid AI, addressed this exact problem in her 2011 doctoral thesis: enabling software agents buying and selling goods to find a common language. She discovered at the time that the difficulty lay not in whether agents could execute actions, but in their fundamentally different understanding of the same word—one side described quotes using synonyms, while the other expressed needs through specific requests.
Fifteen years later, she believes enterprises are rebuilding the same maze. Today, every ERP and CRM tool comes with built-in agents. To check information in Salesforce, employees must consult Salesforce’s agent; to check another CRM, they must consult that CRM’s agent. Pleșea notes this returns organizations to the state of 2011 or earlier—every system exists, yet no one knows where information originates, nor is there a unified source of truth. She argues that what is truly needed is not more agents, but a secure, governable framework that orchestrates all agents in one place and audits what each agent does.
Joe Kim, CEO of Druid AI, offers another perspective. He describes traditional integration as working by design—you pre-draw flowcharts and instruct the system on step one, then step two. Agents, however, work by intent—a salesperson’s true goal is to close the deal, meet targets, and earn bonuses; they may follow processes or bypass them, but the optimization direction is the result itself. Kim believes agents will optimize similarly, so they must be designed from the start to be trustworthy and monitorable, rather than mapped incrementally.