Overview

Poetic builds an AI infrastructure platform that sits on top of existing large language models from providers like OpenAI, Anthropic, Google, and Meta. Rather than creating new models from scratch, Poetic adds an intelligence layer and a set of AI agents that use recursive self-improvement to refine their own reasoning strategies. This approach aims to boost problem-solving ability, accuracy, and efficiency by producing task-specific reasoning systems trained on smaller datasets. The goal is to help organizations get better results from current foundation models without retraining them, using an orchestration of agents and reasoning modules to handle complex tasks across various domains.

Funded Recently