Advancing trustworthy AI through adversarial testing and remediation.
Mace AI helps enterprises deploy AI models and agent harnesses safely. Our mission is Deep Model Trust: building systems and evidence for AI agents operating with real authority across tools, memory, shared state, changing models, and remediation cycles.
Built by leaders from world-class companies and universities:
XBTO
Harvard
ColumbiaVulnerability discovery and remediation of agentic surfaces for highly regulated industries.
Fisher tests configured, tool-using AI agents through adaptive multi-turn conversations. It examines traces and tool calls, uses evolutionary search to discover vulnerabilities, and turns the results into findings, validation evidence, and remediation guidance.
Adaptive multi-turn conversations probe the agent, its tools, and its operating boundaries.
Traces and tool calls are examined through evolutionary search to find novel attack paths.
Findings include replay evidence and guidance your team can use to fix and retest.
Get the grounding and the recorded results behind Fisher.
