Skip to main content
Apollo-1 is the first neuro-symbolic foundation model designed specifically for task-oriented conversational agents. It combines neural networks’ conversational fluency with symbolic reasoning’s reliability, enabling agents that converse naturally while act deterministically.

​
Two Types of Agents

Two different things are emerging under the name “agent.” Open-ended agents work for users. Coding assistants, computer-use agents, personal AI. The user is the principal. If the agent interprets intent slightly differently each time, that’s fine — the user is in the loop and will correct it. Flexibility is the point. Task-oriented agents work on behalf of organizations. An airline’s booking agent. A bank’s support agent. An insurer’s claims agent. A dental clinic’s scheduling assistant. A SaaS company’s onboarding flow. These agents serve users, but they represent the organization. The organization is the principal. These agents manage conversations that run the economy: booking flights, processing payments, managing claims, executing trades. They require both behavioral certainty and conversational flexibility. The organization could be a Fortune 500 or a five-person company. It doesn’t matter. What matters is that when the agent gets something wrong, there’s no user in the loop to catch it. Money moves. Appointments break. Policies are violated. The agent is the loop. So the organization needs more than an agent that works. It needs access to how the agent thinks — so it can direct it, inspect it, debug it, and improve it. It needs an agent whose brain is open. This combination — unified control and flexibility — is the hard problem that Apollo-1 solves.