About Andy Agent Lab

Andy Agent Lab researches how AI reproduces human cognitive, emotional, and social patterns through model training and system architecture.

Andy Agent Lab is an AI research and product development company founded and operated by Tamar Peretz. The company studies how AI reproduces patterns of human cognition, emotion, and social behavior, connecting this research with product development and offensive and defensive AI security.

Research approach

Research starts with the human capability an AI system appears to approximate. The lab examines the corresponding AI behavior and the training processes, underlying mechanisms, and system architectures that produce it. Connecting these levels helps distinguish observed behavior from the mechanisms beneath it and identify human-derived biases, reasoning patterns, capability gaps, and failure modes.

This work includes Theory of Mind and the cognitive, emotional, and social patterns that AI systems can reproduce. The findings inform how models and agents can be trained, evaluated, and improved.

Applied systems and security

The research is tested in proof-of-concept systems. The findings are applied to the design, evaluation, and security of models and agents.

Security analysis is mapped, where relevant, to OWASP risk frameworks for LLM and agentic applications.

Professional training and organizational work

The lab translates research findings into professional training, lectures, and selected work with organizations. This work supports more critical, evidence-based, and controlled use of AI, helping people understand its behavior, evaluate its claims, and apply it with appropriate oversight.

Public knowledge platform

This site is Andy Agent Lab’s free public knowledge platform. It shares part of the lab’s research and applied work with people who use, build, or evaluate AI systems.

  • Articles examine AI behavior, model training and evaluation, prompt engineering, agent architecture, and AI security.
  • Guides provide practical procedures for structured AI-assisted work.
  • Prompts offer reusable task specifications and control patterns.
  • Policies define requirements for evidence, sources, verification, review, and output.
  • Reference material provides technical models, diagrams, terminology, and platform guidance.

The platform is designed to help readers understand AI critically, evaluate its claims, and adopt it with appropriate evidence, oversight, and control.

Published articles relevant to the lab’s research focus include:

Founder: Tamar Peretz

Tamar Peretz, founder of Andy Agent Lab and AI researcher

Tamar Peretz is the founder of Andy Agent Lab, where she leads AI research and product development. Her work spans human-like AI behavior, model and agent evaluation, and offensive and defensive AI security.

This connection allows her to distinguish displayed behavior from the mechanisms beneath it, identify human-derived biases and reasoning patterns reproduced by AI, and explore how models and agents can be trained, evaluated, and improved. Her research includes Theory of Mind and the ways these patterns can affect reliability and security.

Tamar develops proof-of-concept systems and translates the findings into professional training, lectures, and selected work with organizations, supporting more critical, evidence-based, and controlled use of AI.

Follow