AI & ML interests

The independent record of how far autonomous AI can be trusted.

Recent Activity

Gautam-R-Patil聽 updated a Space 4 days ago
TRUSCOR/README
Gautam-R-Patil聽 published a Space 4 days ago
TRUSCOR/README
View all activity

Organization Card

TRUSCOR

The independent record of how far autonomous AI can be trusted.

TRUSCOR Private Limited (Bengaluru, India) tests what AI systems do and records it as evidence others can check. We build open tools for recording, replaying and reproducing AI-agent behaviour, and the .sova format for packaging security findings so anyone can verify them offline.

Research

Did the Attack Really Work? Auditing, Re-running, and Sealing AI-Agent Security Findings with .sova Gautam R. Patil, 2026. Preprint.

We checked a widely used AI-agent security benchmark's verdicts against what the agents actually did, re-ran its attacks on 24 current models from 8 developers, and released every run as .sova files.

Open source

Links

truscor.org 路 GitHub 路 X 路 Bluesky 路 LinkedIn 路 YouTube 路 Zenodo

Founder: Gautam R. Patil

models 0

None public yet

datasets 0

None public yet