LLM Benchmarks: Understanding Language Model PerformanceLearn about key LLM benchmarks, why they should be prioritised for specific tasks, and what metrics should be used to compare LLM performance.Conor Kelly
8 Retrieval Augmented Generation (RAG) Architectures You Should Know in 2025Explore the 8 most popular Retrieval Augmented Generation (RAG) architectures, understand their workflows and use cases for building generative AI applications.Conor Kelly
A look back at 2024: How Humanloop has evolvedIn this post we run through our release highlights from the last year or so, across prompt management, evals and observability.Peter Hayes
Humanloop is moving to General AvailabilityToday we’re excited to open access to Humanloop for all enterprises building AI products with LLMsRaza Habib
10 AI Podcasts to Listen to in 2025A guide on the top podcasts that will help guide your understanding of AI and keep up with the latest advancements and newsConor Kelly
Model DistillationLearn what model distillation is, how it works with OpenAI, its benefits, challenges, and alternative solutions.Conor Kelly
How Replicate is Democratizing AI with Open-Source ResourcesIn this episode, we explore how Replicate is breaking down barriers in AI development through its open-source platform. CEO Ben Firshman shares how Replicate enables developers without machine learning expertise to run AI models in the cloud.Raza Habib
Principles for Building Excellent AI FeaturesIn this episode of High Agency, Raza speaks with Lorilyn McCue, the driving force behind Superhuman’s AI-powered features. Lorilyn lays out the principles that guide her team’s work, from continuous learning to prioritizing user feedback.Raza Habib
LLM GuardrailsLearn how LLM guardrails work, the different types of guardrails and best practices for implementation.Conor Kelly
The Problem with RAG TerminologyJeff Huber covers the evolution of vector databases in AI engineering, challenges common assumptions about RAG and shares insights from Chroma's journey.Raza Habib