Frontier AI security research
The lab behind runtime agent security.
Sondera studies how autonomous agents fail, how human intent becomes enforceable policy, and how runtime evidence proves what happened after an agent acts.
Research presented at
Conferences this research has been presented at
Lab index
Research that turns intent into a decision you can inspect.
-
ICML AIWILD 2026 Paper
Autoformalization of Agent Instructions into Policy-as-Code
A pipeline for translating natural-language agent instructions, tool schemas, and policy documents into checked policy before an agent acts.
-
UnPrompted Talk
Hooking Coding Agents with the Cedar Policy Language
A technical talk on bringing policy into the coding-agent loop so agent actions can be constrained before they complete.
-
LLM Solve Paper
Autoformalization of Agent Instructions into Policy-as-Code
The same autoformalization research direction as the ICML AIWILD work: turning agent instructions and requirements into checked policy.
Featured research
Autoformalization of Agent Instructions into Policy-as-Code.
Accepted to the Second Workshop on Agents in the Wild: Safety, Security, and Beyond at ICML 2026, with the same research direction presented at LLM Solve.
Adam Mondl · Matthew Maisel · John H. Brock
Research architecture
From language to a checked decision.
-
01 · Grounding
Tools become schema.
-
02 · Model layer
Intent becomes policy.
-
03 · Safety layer
Policy gets checked.
Lab agenda
Four research problems. One goal: agents you can prove are acting within bounds.
-
Autoformalization
Intent becomes policy.
Instructions written naturally, tool definitions, and requirements are transformed into policy that can be checked before an action runs.
-
Runtime enforcement
Actions meet boundaries.
The security decision moves to the moment an agent asks to read, write, call a tool, or move data across a boundary.
-
Trajectory evidence
Behavior becomes inspectable.
The research program treats agent behavior as a trajectory: context, tool calls, policy attributes, verdicts, and the rule path behind them.
-
Scalable oversight
Humans should not review every action.
Sondera studies how policy, monitors, and evidence can help security teams supervise agent fleets without turning autonomy back into manual approval.
Put the research to work