> Markdown version of [/events/world-congress-2025/sessions/603-beyond-the-prompt](https://www.wearedevelopers.com/events/world-congress-2025/sessions/603-beyond-the-prompt). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Beyond the Prompt: Evaluating, Testing, and Securing LLM Applications


- **Date:** Thursday, Jul 10, 2025
- **Time:** 14:10–14:40 (30 min)
- **Room:** Stage 2
- **Event:** World Congress 2025
- **Tags:** ai, automation, cybersecurity, llms, testing

## Description

When you change prompts or modify the Retrieval-Augmented Generation (RAG) pipeline in your LLM applications, how do you know it’s making a difference? You don’t—until you measure. But what should you measure, and how? Similarly, how can you ensure your LLM app is resilient against prompt injections or avoids providing harmful responses? More robust guardrails on inputs and outputs are needed beyond basic safety settings.

In this talk, we’ll explore various evaluation frameworks such as Vertex AI Evaluation, DeepEval, and Promptfoo to assess LLM outputs, understand the types of metrics they offer, and how these metrics are useful. We’ll also dive into testing and security frameworks like LLM Guard to ensure your LLM apps are safe and limited to precisely what you need.

## Speaker

### [Mete Atamel](https://www.wearedevelopers.com/@mete-atamel)

Software Engineer and Developer Advocate at Google


## Related talks at this congress

- [Prompt Injection, Poisoning & More: The Dark Side of LLMs](https://www.wearedevelopers.com/events/world-congress-2025/sessions/828-prompt-injection) — Keno Dreßel
- [Beyond the Hype: Building Trustworthy and Reliable LLM Applications with Guardrails](https://www.wearedevelopers.com/events/world-congress-2025/sessions/552-beyond-the-hype) — Alex Soto
- [ The Limits of Prompting: ArchitectingTrustworthy Coding Agents](https://www.wearedevelopers.com/events/world-congress-2025/sessions/637-the-limits-of) — Nimrod Kor
- [A Jumpstart to Using LLMs for Test Design](https://www.wearedevelopers.com/events/world-congress-2025/sessions/464-a-jumpstart-to-using) — Pierre Baum, Rahul