Okay, Evidently AI has an awesome, massive collection of 600+ System Design blogs ranging ML, Rec systems, Optimisation, Gen AI from across companies in a number industries. Best part is that you can filter according to your needs on a number of categories.

🤖 How do I trust GenAI? Klaviyo shares its methodology for evaluating LLM-powered features and how they improved prompt engineering with good old software design patterns 👇 klaviyo.tech/how-do-i-trust…

A Friday ML use case 📕 📚 From the database of 500 ML & LLM systems: cutt.ly/SwrZWL0g How Upwork’s hiring AI assistant helps companies draft job posts and compare candidate proposals to find the right fit. upwork.com/blog/scaling-a…

📌 In case you missed it LLM evaluation workflows and tools explained! The guide explains how to design an LLM evaluation framework for your AI application and introduces Evidently, an open-source LLM evaluation tool. evidentlyai.com/blog/llm-evalu…

Building foundation models into an AI platform Nubank shares its approach to productionizing Foundation Models using the bank’s AI platform and how it develops technologies and tools to drive Foundation Model projects 👇 building.nubank.com/foundation-mod…

A Friday ML use case 📕 📚 From the database of 500 ML & LLM systems: cutt.ly/SwrZWL0g How Grab leverages RAG-powered LLMs to automate routine analytical tasks, such as generating regular reports. engineering.grab.com/transforming-t…

📌 In case you missed it How to test your Gen AI app in 2025? The blog breaks down the OWASP Top 10 LLM list of vulnerabilities for LLM apps and shows how to apply them to keep your AI product safe and reliable 👇 evidentlyai.com/blog/owasp-top…

✍️ Harnessing the power of customer feedback with LLMs Meta shares how they developed a self-service AI tool to help understand customer preferences and their influence on product sentiment. medium.com/@AnalyticsAtMe…

11th annual MAD (Machine Learning, AI & Data) Landscape is out 🚀 We are pleased to be featured in the AI Observability and Evaluation category 🔥 Thanks to Matt Turck et al. for putting it together and mentioning @EvidentllyAI! Check it out: mattturck.com/mad2025

A Friday ML use case 📕 📚 From the database of 500 ML & LLM systems: cutt.ly/SwrZWL0g How LinkedIn automates hiring routine tasks with an agent-based AI assistant that helps find candidates, review applications, and write role qualifications. linkedin.com/pulse/introduc…

📌 In case you missed it 7 RAG benchmarks! Building with RAG? Here are 7 RAG benchmarks that test how well different LLMs handle core RAG challenges like grounded reasoning and using retrieved evidence 👇 evidentlyai.com/blog/rag-bench…

A Friday ML use case 📕 📚 From the database of 650 ML & LLM systems: cutt.ly/SwrZWL0g How Instacart helps users find new products by incorporating LLMs into the search stack to generate discovery-oriented content. tech.instacart.com/supercharging-…

📊 What's your go-to MLOps stack? The State of MLOps Survey is live – and we’re excited to see the first results, where Evidently is the most popular tool for ML monitoring 🔥 Kudos to Alejandro Saucedo | KubeCon 2025 AI Day Keynote for this insightful research! You can still vote here 👇 docs.google.com/forms/d/e/1FAI…

📌 In case you missed it 8 AI hallucinations examples 🦄 We put together eight examples of real-world AI hallucinations – from a transcription tool fabricating texts to citing made-up company policies. Explore the examples 👇 evidentlyai.com/blog/ai-halluc…

❓ 7 questions about LLM judges! We answered some of the most common questions we get about how LLM judges work and how to use them effectively 👇 evidentlyai.com/blog/llm-judge…