Thomas Luechtefeld is an entrepreneur and AI researcher dedicated to building tools that improve public health and safety. As the founder of Insilica.co, he has developed platforms like Sysrev, an AI assisted document review tool, and Biobricks.ai, a data registry for open chemical and biological data. Thomas specializes in applying artificial intelligence to challenges in toxicology, chemical safety, and environmental health. He has collaborated with academic and industry partners on projects that advance open science and improve data accessibility. With a focus on practical solutions, his work supports better decision-making and fosters collaboration across disciplines
The Persistent Agent: Orchestrating AI, Knowledge Graphs, and Predictive Toxicology for a Safer World
The Persistent Agent framework unifies large language models, predictive tools, and interoperable knowledge graphs to automate toxicological reasoning. Built around ToxIndex, it integrates retrieval-augmented prediction with the BioBricks-OKG data registry, enabling agents to collect evidence, run models, and generate structured hazard assessments. This system links chemical structure, mechanistic pathways, and literature evidence across sources, turning fragmented data into coherent, interpretable predictions. Benchmarks show strong performance across major toxicity datasets (AUC > 0.9) and substantial gains from retrieval-augmented prediction for endpoints such as LC₅₀ inhalation toxicity (R² = 0.74). Case studies, including PFAS hepatotoxicity and neurotoxicity analysis, demonstrate how persistent, agentic workflows can support hazard surveillance and safer material design. Together, these components illustrate a scalable approach to predictive toxicology: continuously updated, interpretable, and aligned with the goal of a safer world.