PinnedSumit Soman·Feb 25, 2025Testing & Evaluating Large Language Models(LLMs): Key Metrics and Best Practices Part-1Large Language Models (LLMs) have revolutionized natural language processing (NLP), powering applications in text generation…A response icon1A response icon1
Sumit Soman·Apr 14, 2025AI-driven Test Automation with Playwright + MCP Server + CursorAIIn this post, we’ll explore how to leverage AI-assisted code generation using Playwright, MCP Server, and Cursor IDE to build a robust test…A response icon1A response icon1
Sumit Soman·Mar 14, 2025Mastering LLM Evaluation with DeepEval: A Hands-on GuideAs LLMs continue to evolve, evaluating their outputs for accuracy, coherence, and reliability has become increasingly important. DeepEval…
Sumit Soman·Feb 25, 2025Testing & Evaluating Large Language Models(LLMs): Key Metrics and Best Practices Part-3Welcome to the third and final part of our blog series on “Testing & Evaluating Large Language Models (LLMs): Key Metrics and Best…A response icon1A response icon1
Sumit Soman·Feb 25, 2025Testing & Evaluating Large Language Models(LLMs): Key Metrics and Best Practices Part-2In the first part of this blog series, we explored a range of evaluation metrics for Large Language Models (LLMs), covering everything from…A response icon2A response icon2
Sumit Soman·Feb 17, 2025Building an OpenAI-Powered RAG Chatbot and Testing it with RAGASIn this blog, we will build a Library AI Assistant powered by Large Language Models (LLMs) OpenAI, and ChromaDB for efficient knowledge…A response icon1A response icon1
Sumit Soman·Feb 15, 2025Browser-use with OpenAI + Langchain for Automating Web BrowsingIn this blog, we will explore how to utilize browser-use in conjunction with LangChain and OpenAI’s GPT-4o to find the most affordable…A response icon3A response icon3
Sumit Soman·Feb 9, 2025Automating RAG Pipeline Evaluation with RAGAS: A Testing Framework for RAG ApplicationsRetrieval-Augmented Generation (RAG) enhances AI applications by integrating large language models (LLMs) with external knowledge sources…
Sumit Soman·Feb 4, 2025MCP Meets Claude: Unlocking the Future of AI Agents with Model Context ProtocolLLM’ is evolving rapidly, and with it comes the need for better interoperability, context awareness, and seamless integration across…
InDevOps.devbySumit Soman·Feb 3, 2025Shift-Left Observability: Visualizing k6 Load Tests with Prometheus & GrafanaObservability is a key pillar of performance testing, ensuring that you can monitor, analyze, and optimize system behavior in real time. In…