Letter from the CEO: Handshake acquires Cleanlab

Cleanlab has been acquired by Handshake AI.

Curtis Northcutt

Real-Time Error Detection for LLM Structured Outputs: A Comprehensive Benchmark

Tools to automatically detect errors in Structured Outputs or Extracted Data produced by any LLM.

Hui Wen Goh & Jonas Mueller

Automated Hallucination Correction for AI Agents: A Case Study on Tau²-Bench

Evaluating autonomous failure prevention for AI agents on the leading customer service AI benchmark.

Tianyi Huang & Jonas Mueller

Expert Guidance: Teaching Your AI How to Behave

The Emerging Reliability Layer in the Modern AI Agent Stack

Expert Answers: The Easiest Way to Improve Your AI Agent

LLM Structured Output Benchmarks are Riddled with Mistakes

Managing AI Agents in Production: The Role of People

AI Agent Safety: Managing Unpredictability at Scale

Benchmarking real-time trust scoring across five AI Agent architectures

Prevent Hallucinated Responses from any AI Agent

Learn about Data-Centric AI