---
type: "post"
id: "just-ai-published-a-technical-account-of-training-0e5091"
slug: "just-ai-published-a-technical-account-of-training-0e5091"
title: "Just AI published a technical account of training jailbreak and prompt-injection detectors for"
description: "Just AI published a technical account of training jailbreak and prompt-injection detectors for Russian-language AI agents in its Jay Guard product."
retrieval_nugget: "Just AI published a technical account of training jailbreak and prompt-injection detectors for Russian-language AI agents in its Jay Guard product."
published_at: "2026-10-21"
updated_at: "2026-10-21"
record_date: "2026-10-21"
date_kind: "published_at"
topics: ["mcp"]
entities: ["Just AI","Jay Guard","GPT-OSS Safeguard","Llama Guard 4","DeBERTa","MCP"]
related_patterns: ["agent-security-moves-to-runtime-boundaries"]
novelty_label: "same_event"
what_changed: "Same event as Как мы обучили детектор джейлбрейков для русскоязычных AI-агентов Привет, Хабр!"
prior_refs: ["memory:2e7181a4-9660-87da-aa3b-a2f48f94cf65"]
source_url: "https://habr.com/ru/companies/just_ai/articles/1084804"
source_urls: ["https://habr.com/ru/companies/just_ai/articles/1084804"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:just-ai-published-a-technical-account-of-training-0e5091"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/just-ai-published-a-technical-account-of-training-0e5091/","markdown":"https://newruntime.com/posts/just-ai-published-a-technical-account-of-training-0e5091.md","json":"https://newruntime.com/posts/just-ai-published-a-technical-account-of-training-0e5091.json"}
---

# Just AI published a technical account of training jailbreak and prompt-injection detectors for

## Retrieval answer

Just AI published a technical account of training jailbreak and prompt-injection detectors for Russian-language AI agents in its Jay Guard product.

Just AI published a technical account of training jailbreak and prompt-injection detectors for Russian-language AI agents in its Jay Guard product. The company describes Jay Guard as a security layer between an application and an LLM, checking attacks, content, and personal data.

The team evaluated GPT-OSS Safeguard 20B, Llama Guard 4 12B, and a fine-tuned 184M-parameter DeBERTa model. Its validation set contained 436 Russian- and English-language jailbreak and injection examples plus 121 benign requests from logs. With default policies in zero-shot use, GPT-OSS Safeguard recorded F1 of 0.57 and 38% false positives on benign requests; Llama Guard 4 recorded F1 of 0.45 and 45% false positives. The fine-tuned DeBERTa recorded F1 of 0.93 and 1.7% false positives.

Just AI distinguishes a guard model, which classifies text, from a guardrails system that combines specialised detectors, policies, thresholds, and enforcement points. It also notes that text detection does not address supply-chain threats such as malicious MCP servers or poisoned weights.

The source does not establish that these results generalise beyond its validation data, default configurations, or operational policies. https://habr.com/ru/companies/just_ai/articles/1084804

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Mcp](https://newruntime.com/topics/mcp.md): Explore the mcp topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)