Stay Confident
Subscribe to our weekly newsletter to stay confident in the AI systems you build.
LLM Arena-as-a-Judge: LLM-Evals for Comparison-Based Regression Testing
In this article, you'll learn everything about running LLM Arena-as-a-judge as a novel way to regression test LLMs.
Jeffrey Ip
RAG Evaluation Metrics: Assessing Answer Relevancy, Faithfulness, Contextual Relevancy, And More
This article will go through everything you'll need for RAG evaluation, including metrics, and best practices.
Jeffrey Ip
LLM Evals Framework That Predicts ROI: A Step-by-Step Guide
Most LLM evals fail because metrics don't predict ROI, build outcome-based evals that correlate with business KPIs.
Jeffrey Ip
G-Eval Simply Explained: LLM-as-a-Judge for LLM Evaluation
This article goes through everything on G-Eval for anyone to easily evaluate LLM apps on any task specific criteria.
Kritin Vongthongsri
Top LLM Evaluators for Testing LLM Systems at Scale
In this article, we'll go through all the top LLM evaluators in 2025 including G-Eval and other LLM-as-a-judges.
Jeffrey Ip
How I raised Confident AI's $2.2M seed round in 5 days
Announcing Confident AI's seed round, with participation from a bunch of great investors.
Jeffrey Ip
How I Built Deterministic LLM Evaluation Metrics for DeepEval
In this article, I'm sharing how I've built DeepEval's latest deterministic, LLM-powered, custom metric.
Jeffrey Ip
LLM Agent Evaluation Metrics in 2026: Tool Calling, Task Completion, Reasoning, and Trace-Based Evals
Learn how to evaluate LLM agents end-to-end with tool calling, task completion, reasoning, trace-based evals, human review, and DeepEval code examples.
Kritin Vongthongsri
LLM Guardrails for Data Leakage, Prompt Injection, and More
In this article, you'll learn everything you need to know on LLM guardrails and how to use it for LLM security.
Jeffrey Ip
OWASP Top 10 2025 for LLM Applications: What’s new? Risks, and Mitigation Techniques
In this article, we'll go through what is OWASP Top 10, as well as what's new in their latest 2025 guidelines.