The Millimetre Problem: Introducing the lab-hardware-cad Agent Skill
Introducing lab-hardware-cad, an open-source Agent Skill that turns any AI agent into a CAD engineer for lab hardware, benchmarked over 98 geometry-scored runs.
Blog
Insights & Updates
Explore tutorials, product updates, and insights on AI-powered research automation from the K-Dense team.
Filter by:AllAIARPA-HBenchmarkBenchmarksBioinformaticsBiologyBiomarker DiscoveryBiotechCase StudyChemistryClinical TrialsCommunityCompetitive IntelligenceData ScienceDrug DevelopmentDrug DiscoveryDue DiligenceEnterpriseFDAFinanceGBMGPUGoogleHardwareHealth PolicyHealthcareImage ModelsImmunotherapyInvestment AnalysisK-Dense BYOKK-Dense WebMachine LearningMass SpectrometryMedical DevicesMetabolomicsMultimodalNVIDIANeoantigenOSINTOncologyOpen SourceOpinionPartnershipPhDPharmaProductProteomicsPublic HealthPublic PolicyReproducibilityResearchResearch FundingResearch PlanningRoboticsScienceScientific Agent SkillsScientific IntegrityScientific VisualizationSecuritySkillsTranslational ResearchTutorialUAPUse Case
Introducing K-Bench 01: Nine Frontier Models, 178 Real Scientific Tasks, and a Lot of Confident Wrong Answers
K-Bench 01 is our internal benchmark built from 178 real scientific tasks. Nine frontier models ran them end to end; only one clears the acceptability bar.
K-Dense Web and Litmus Science: Closing the Loop from Hypothesis to Experiment
K-Dense and Litmus Science are connecting AI-powered research with on-demand lab execution, helping scientists move from questions to evidence faster.
AI Co-Scientists, Answered: 20 Questions from a Live Session with a University Research Center
Twenty questions from a live session with a university multiomics center on what K-Dense does, where AI for science helps today, and where it still falls short.
K-Dense Web vs. Claude Science: K-Dense Leads on Execution and Overall Score
A 20-task benchmark found K-Dense Web stronger at producing auditable research bundles, while Claude Science held a narrow scientific-quality lead.
Benchmarking Google's Omni Flash for Scientific Video
A 35-case K-Dense benchmark of Google's Omni Flash shows stunning scientific video quality, but unreliable text, physics, and factual correctness.
Benchmarking Nano Banana 2 Lite for Scientific Image Generation
A 240-image benchmark of four scientific image models shows Nano Banana 2 Lite is fastest, while GPT Image 2 still leads on raw figure quality.
AI Scientists Need Lab Escape Rooms, Not More Exams
The next AI scientist benchmark should be a lab escape room: a fresh hidden world, limited probes, real evidence, and no place for science theater to hide.
Benchmarking NVIDIA BioNeMo Agent Toolkit Skills for NIM microservices
A controlled benchmark of 10 NVIDIA BioNeMo Agent Toolkit skills for NIM microservices shows where skills win: routing, cost, scale, and weak-model reliability.