# Charmed Kubeflow

Published articles for Charmed Kubeflow.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Realtime transaction fraud detection - with an LLM?

DevFeed: [Realtime transaction fraud detection - with an LLM?](<https://devfeed.tech/articles/realtime-transaction-fraud-detection-with-an-llm-62477.md>)

Original publisher: [Read original article](<https://ubuntu.com//blog/realtime-transaction-fraud-detection-with-an-llm>)

Author: Rob Gibbon (Rob Gibbon)

Published: 2026-09-30T06:58:49Z

Content type: tutorial

Language: en

Sources: [Ubuntu blog](<https://devfeed.tech/sources/ubuntu-blog.md>)

Topics: [Payment Fraud](<https://devfeed.tech/topics/payment-fraud.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [charmed-kubeflow](<https://devfeed.tech/tags/charmed-kubeflow.md>), [classification](<https://devfeed.tech/tags/classification.md>), [follow](<https://devfeed.tech/tags/follow.md>), [index](<https://devfeed.tech/tags/index.md>), [kserve](<https://devfeed.tech/tags/kserve.md>), [kubernetes](<https://devfeed.tech/tags/kubernetes.md>), [llms](<https://devfeed.tech/tags/llms.md>), [mlops](<https://devfeed.tech/tags/mlops.md>)

### AI overview

The tutorial introduces a real-time transaction fraud detection project using the open-weight system-one-qwen3.5-4b-scorer model. It explains how modified language models return classification probabilities without generating text and outlines deployment with KServe on Kubernetes, including local hardware and software prerequisites.

### Source excerpt

Conversational AI with a chatbot is great for drafting emails or debugging code, but it's less ideal for real-time application middleware. If you're trying to inspect a financial transaction for potential fraud in the middle of a checkout loop, you don't need an LLM to write you an essay about why a credit card transaction [...]