# Enkrypt AI

> Enkrypt AI is a Boston-based AI security company that builds a control layer between enterprises and the large language models and AI agents they deploy. Founded in 2022 by Yale PhDs Sahil Agarwal and Prashanth Harshangi, its Sentry platform combines automated red teaming, runtime guardrails, and compliance monitoring to detect vulnerabilities like prompt injection, jailbreaks, bias, and data leakage before and after models reach production. The company also publishes a free LLM Safety Leaderboard and widely cited red-team research, including a January 2025 report finding DeepSeek-R1 far more likely than rivals to produce harmful content.

- **Founded:** 2022
- **Headquarters:** Boston, Massachusetts, United States
- **Founders:** Sahil Agarwal (Co-founder & CEO), Prashanth Harshangi (Co-founder & CTO)
- **Team size:** ~22 employees
- **Products:** Sentry Platform, Agent Red Teaming, Agent Guardrails, Agent Policy Engine, AI Data Risk Audit
- **Notable:** Published the industry's first LLM Safety Leaderboard, benchmarking 200+ models for free., Widely cited January 2025 DeepSeek-R1 red-team report picked up by Axios, Infosecurity Magazine, TechRadar, and the Cloud Security Alliance., Raised a $2.35M seed round in February 2024 led by Boldcap.

## Products & services

- **Sentry Platform** — An end-to-end AI security suite that acts as a control layer between users and LLMs, spanning red teaming, guardrails, and compliance.
- **Agent Red Teaming** — Automated, continuous adversarial testing that probes models and agents for prompt injection, jailbreaks, bias, and CBRN misuse before and after deployment.
- **Agent Guardrails** — Runtime protection at scale that redacts sensitive data, blocks harmful prompts, and enforces policy on live AI systems.
- **Agent Policy Engine** — Tooling to define and enforce use-case-specific policies across an organization's AI agents.
- **AI Data Risk Audit** — Audits training data, fine-tunes, and embeddings for privacy and security risk.
- **MCP Gateway** — A single secured endpoint for connecting to Model Context Protocol servers.
- **MCP Scanner** — Scans MCP servers for security risks and misconfigurations.
- **LLM Safety Leaderboard** — A free public benchmark ranking 200+ models on safety and hallucination risk via continuous red teaming.

## Achievements

- Published the industry's first LLM Safety Leaderboard, benchmarking 200+ models for free.
- Widely cited January 2025 DeepSeek-R1 red-team report picked up by Axios, Infosecurity Magazine, TechRadar, and the Cloud Security Alliance.
- Raised a $2.35M seed round in February 2024 led by Boldcap.
- Launched a purpose-built AI agent security solution in April 2025.
- Research preprint on increased LLM vulnerabilities from fine-tuning and quantization.

## Latest updates

- **2024-02** — Raised $2.35M seed round led by Boldcap to build a visibility and security layer for generative AI.
- **2025-01** — Published red-team report finding DeepSeek-R1 11x more likely than rivals to generate harmful content; report cited widely across security press.
- **2025-04** — Launched a dedicated AI agent security solution to mitigate risk and non-compliance in autonomous agent deployments.
- **2026-02** — Introduced tooling to secure AI coding assistants as part of the expanding Sentry suite.

## Links

- Website: https://enkryptai.com
- LinkedIn: https://www.linkedin.com/company/enkryptai/
- Twitter/X: https://x.com/enkryptai
- GitHub: https://github.com/enkryptai
- YouTube: https://www.youtube.com/@enkryptai

---

Profile page: https://yespress.io/enkrypt-ai
Published by YesPress — https://yespress.io
Last updated: 2026-08-06