Resources
Tools, videos, and articles for successful AI guardrails and governance implementation
Featured
Improving knowledge graph creation in life sciences through agent steering
Agent steering intercepts agents mid-run to provide state-specific feedback, improving completeness, hallucination rates, and entity resolution by up to 14 percentage points for knowledge graph creation in life sciences.
Hallucination Detection Comparison
What's the best tool for hallucination detection? We put 7 of them to the test.
Where AI?
Find which cloud provider hosts your AI model, in which regions, and with what data residency guarantees.
Try it nowMore Resources
PlaceboBench: An LLM Hallucination Benchmark for Pharma
We created PlaceboBench, a challenging pharmaceutical RAG benchmark based on real clinical questions and official EMA documents. Twelve state-of-the-art LLMs show hallucination rates between 24% and 64%.
Four ways to reduce hallucinations in your AI agents
Sharing 4 approaches to reducing hallucinations, backed by quantitative evidence.
PlaceboBench findings: Which LLM hallucinates most on Pharma data?
We ran 12 of the latest LLMs against a challenging use case in Pharma. Watch to find out how often models hallucinated, why the model with the lowest hallucination rate might not be the best option, and how latency and cost should inform your model selection.
Building Hallucination Resistant GenAI Applications in Pharma
We tested 12 state of the art LLMs like GPT-5.4 or Gemini 3.1 Pro on a challenging use case in Pharma. This resulted in PlaceboBench, a benchmark on hallucination rates in Pharma. This on-demand session walks through detailed results and strategies to mitigate hallucinations.
What does it cost to do OCR with Large Language Models?
Our LLM OCR Cost Calculator allows AI builders to compare PDF parsing costs across different LLM providers and models
OCR Cost Calculator
Compare OCR processing costs across major LLM providers. Find the most cost-effective solution for your PDF parsing job.
Try it now
How to create your own hallucination detection benchmarks: Making of the RAGTruth++ dataset
We walk you through the process of creating the RAGTruth++ hallucination benchmark. Useful for anyone who wants to get a deeper understanding of how benchmarks are made.
RAGTruth++: Enhanced Hallucination Detection Benchmark
We enhanced the RAGTruth benchmark by finding 10x more hallucinations through automated detection and human review.
Why Hallucination Benchmarks Miss the Mark
The gap between hallucination benchmarks and production reality and what bears have to do with it
AI Hallucinations - Reverse engineering Azure Groundedness and building your own hallucination detector
Learn how to reverse engineer Azure's Groundedness detection system and build your own custom hallucination detector for AI applications.