Resources · Blog · Tag

LLM engineering.

Building with large language models — observability, latency, deployment.

Tagged “LLM engineering”

How to Strengthen Ransomware Protection Against Modern Attacks

AI in Cybersecurity24 Jun 2026

LLM Refusal Behavior on Open-Weight Model

Written by: Trimikha Valentius (CAIO, Head of ZENTARA Labs), Alisha Deana (AI Researcher) Conversational language models refuse harmful requests because a thin behavioural layer is added on top of a pretrained base during post-training. This article treats refusal as exactly that: a layer, not a pro

Trimikha Valentius

AI in Cybersecurity09 Apr 2026

Securing Enterprise Copilots: Preventing Prompt Injection and Data Exfiltration in LLMs

Organisations are rapidly adopting AI copilots powered by large language models (LLMs) to enhance productivity, decision-making, and workflow automation. However, with this convenience comes a new category of risk. Recent research published in 2026 highlights that LLM prompt injection vulnerabilitie

Trimikha Valentius

Technical Guides07 Apr 2026

A Recipe for Langchain LLM Observability using Langfuse

When a standard app fails, you check the stack trace. But when an agent fails, you don’t know what to do. Is the model stuck in a recursive loop? Did it misunderstand the tool output? Is the “Critique Agent” currently hallucinating a list of reasons why the “Research Agent&#8

Adam

AI in Cybersecurity31 Mar 2026

The Hidden Security Risks in AI Adoption: Model Access and Data Leakage

AI adoption is accelerating across industries. From customer support automation to internal analytics and decision-making, organisations are embedding AI into critical workflows at speed. The promise is clear: faster insights, improved efficiency, and competitive advantage. What is less visible is t

Trimikha Valentius

LLM Observability Langchain Langfuse Zentara

AI in Cybersecurity27 Feb 2026

A Recipe for Langchain LLM Observability Using Langfuse

Adam

Blog01 Feb 2026

This Is How We Reduced LLM Security Risks

We are shipping faster, but are we shipping safer? An LLM-based coding tool is an essential part of modern software development, particularly for teams that aim to ship features at an incredible speed. Every engineer must use these tools to stay competitive. Especially when GitHub data shows develop

Adam