$ whoami
operator Adarsh Arun
role AI Safeguards Engineering Intern @ XelerAIT
location Bengaluru, IN
education BE CSE, BNM Institute of Technology
focus AI guardrails / LLM security / detection engineering
shipping Wardline — Rust guardrail library (pre-alpha)
open source roostorg/osprey — PR #451 merged
uptime since Aug 2023Most of what I build answers one question: what happens when this model is given something it should refuse? At XelerAIT I design guardrails for production agentic AI in healthcare — safety, reliability, and compliance enforced at the framework layer rather than bolted on after an incident.
PROMPT ──▶ BROKER ──▶ SCHEMA ──▶ MODEL ──▶ AUDIT
untrusted regex + structured policy- verdict
input metaprompt json bound call log
An embeddable guardrail evaluation library for Rust. Guards run inline in the request path — before an action is taken or an LLM response is released — and return a blocking verdict: allow, block, or modify. A library you call in-process, not a proxy you deploy: no separate service, no network hop, no async runtime. Guards are ordinary Rust implementing one trait, so a guard is testable like any other code.
| Project | What it is |
|---|---|
|
Wardline |
Embeddable, synchronous, trait-based guardrail library. Four-crate workspace with panic isolation and a bounded audit trace. |
|
ISTVON Prompt Engine |
Security broker for LLM prompts — dual-layer regex + metaprompt screening, JSON structuring that isolates malicious payloads, audited verdicts. |
|
Vendor Risk Assessor |
Hierarchical agent pipeline over an MCP tool server. Risk score computed deterministically in Python — the LLM writes prose, never the number. |
|
Telecom SOC Simulation |
DFIR automation with RAG-backed MITRE ATT&CK mapping over MDE investigation packages. |
|
Adaptive Triage Engine |
RL policy that scores and triages SOC alerts from forensic feature data, evaluated on reward distributions and precision-recall trade-offs. |
|
Satellite Land-Use |
Custom CNN vs. ResNet50 vs. VGG16, benchmarked head-to-head on EuroSAT imagery. |
More projects
- AI-Powered Educational Feedback System — NLP analysis of student writing and code. Sentiment via VADER and RoBERTa, readability metrics, style checks, and a Python path that flags syntax, logic, efficiency, and PEP 8 issues with fixes.
- Retail Analytics Dashboard — Apriori market-basket rules and RFM customer segmentation over a year of UCI Online Retail transactions.
- Multi-Client Group Chat — Low-latency messaging on raw Java TCP/IP sockets; multi-threaded server with synchronized broadcasting.
roostorg/osprey #451 — merged upstream into Roost's trust & safety rules engine.
docker compose upfailed on Windows because Git's defaultcore.autocrlf=truechecks out*.shwith CRLF, turning the shebang into#!/bin/bash\r— surfacing as a misleadingno such file or directory. The repo's pre-commit hook fixed line endings at commit time; nothing enforced LF at checkout time. Two lines of.gitattributes, zero content churn.
Security — LLM guardrails · prompt-injection defense · MITRE ATT&CK mapping · DFIR pipelines · alert triage · compliance architecture
AI — RAG · contextual bandits · Model Context Protocol · multi-agent orchestration
Threat-model before you optimize.
A guardrail you cannot audit is a guess.
Latency and cost are safety properties too.