---
title: "Ania Danilec (@annadanilec) | Hashnode"
description: "Advocating for OWASP Top 10 for LLM applications in real-world production environments,. Read the latest articles by Ania Danilec on Hashnode."
url: "https://hashnode.com/@annadanilec"
---

@annadanilec

# Ania Danilec

@annadanilec · Prague, Czech Republic · Joined May 2026

Advocating for OWASP Top 10 for LLM applications in real-world production environments,

### [RAG Evaluation with RAGAS: Measuring Faithfulness, Context Precision, and Recall in Production](https://anna-danilec.hashnode.dev/rag-evaluation-with-ragas-measuring-faithfulness-context-precision-and-recall-in-production?utm_source=hashnode&utm_medium=feed)

Key takeaways: RAGAS gives you four core metrics that split RAG failures into retrieval vs. generation problems Faithfulness catches hallucinations; Context Recall catches retrieval gaps Most metri

14 min read · [anna-danilec.hashnode.dev](https://anna-danilec.hashnode.dev/rag-evaluation-with-ragas-measuring-faithfulness-context-precision-and-recall-in-production?utm_source=hashnode&utm_medium=feed)

[May 18](https://hashnode.com/posts/rag-evaluation-with-ragas-measuring-faithfulness-context-precision-and-recall-in-production/6a0ae3ebe4a28cf570f92465)

### [How we built an MCP Guardrail to enforce Tech Policy in real-time](https://anna-danilec.hashnode.dev/how-we-built-an-mcp-guardrail-to-enforce-tech-policy-in-real-time?utm_source=hashnode&utm_medium=feed)

In 2026, most mid-sized and large organizations are aggressively adopting AI coding assistants such as Cursor, Claude Desktop and Windsurf. Developers are now generating a significant portion of code

14 min read · [anna-danilec.hashnode.dev](https://anna-danilec.hashnode.dev/how-we-built-an-mcp-guardrail-to-enforce-tech-policy-in-real-time?utm_source=hashnode&utm_medium=feed)

[May 12](https://hashnode.com/posts/how-we-built-an-mcp-guardrail-to-enforce-tech-policy-in-real-time/6a02c9a2937b84f7791d6cd6)

### [Deterministic Guardrails for Non-Deterministic Agents](https://anna-danilec.hashnode.dev/deterministic-guardrails-for-non-deterministic-agents?utm_source=hashnode&utm_medium=feed)

By design, Large Language Models (LLMs) are non-deterministic. Even with an identical prompt, they can return different answers, trigger the wrong API, leak sensitive personal data, or initiate a cost

15 min read · [anna-danilec.hashnode.dev](https://anna-danilec.hashnode.dev/deterministic-guardrails-for-non-deterministic-agents?utm_source=hashnode&utm_medium=feed)

[May 8](https://hashnode.com/posts/deterministic-guardrails-for-non-deterministic-agents/69fdc7e06fb09594bd42e1ec)
