Apollo is an agentic language model using neuro-symbolic architecture instead of transformers. Companies of any kind can fine-tune Apollo to deploy Controllable Agents with superior tool use, steerability and overall performance over GPT Agents.
Contact sales
About Apollo
Apollo is an agentic Language Model that replaces the transformer with a Neuro-symbolic architecture built for agents. Developed over the past six years in collaboration with 60,000 human agents, Apollo outclasses traditional LLMs in agentic use-cases. Apollo is trained on a neuro-symbolic language that constitutes both descriptive and procedural ("agentic") data, replacing autoregressive inference with agentic reasoning producing both language and instructions for actions. This method relies on obtaining a structured interaction state, achieved through sensory data collected to produce a symbolic, parameterized representation of each interaction.
Apollo enables companies of any kind to deploy Controllable Agents, versions of Apollo that are fine-tuned on a specific task. Controllable Agents offer fine-grained control, adhere to the deploying company’s policies and provide a white-box view of their decision-making and reasoning. They enjoy superior tool use, steerability and overall performance over GPT Agents.
