Author
Co-Founder & CTO, K-Dense
Timothy Kassis is co-founder and CTO of K-Dense, where the team builds AI agents that run real scientific analysis end to end. Most of the writing here covers agent benchmarks, the open-source Scientific Agent Skills library, and what it takes to make automated research reproducible.
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.
A microbiome foundation model silently discards 97% of a malformed table and returns a valid embedding. We measured what an Agent Skill does about that.
Real research runs on a self-hosted Multica workspace using K-Dense Scientific Agent Skills: trials, variants, literature, and cross-model review.
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.
A 20-task benchmark found K-Dense Web stronger at producing auditable research bundles, while Claude Science held a narrow scientific-quality lead.
A 35-case K-Dense benchmark of Google's Omni Flash shows stunning scientific video quality, but unreliable text, physics, and factual correctness.
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.
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.
A controlled benchmark of 10 NVIDIA BioNeMo Agent Toolkit skills for NIM microservices shows where skills win: routing, cost, scale, and weak-model reliability.
AI is flooding science with claims no one can check. The quieter story: agents now reproduce most published findings — and that is the bigger deal.
A reproducible 250-run study of feature detection, adduct grouping, quantification, and identification, run by an AI agent with and without the pyOpenMS skill.
Fable 5 and GPT-Rosalind show frontier AI moving into scientific workflows. The next bottleneck is not intelligence, but evidence.
A reproducible study of pKa, logD, tautomers, ADME, and docking run by an AI agent with the Rowan skill, measured against RDKit and experimental ground truth.
Anthropic showed a general model can rival ChemDraw at NMR. The real story for scientists: the bottleneck has moved from the model to the workflow around it.
AI agents are moving into real scientific workflows. The question for working scientists is not whether they are powerful, but whether they are verifiable.
Scientific Agents: 503 open-source AGENTS.md profiles that teach any AI agent to reason like a senior practitioner in a specific science or engineering field.
One Agent Skill gives a research agent 78 public scientific and economic databases. Here is the design argument, with real token and routing benchmarks.
Our new open source methodology makes AI research agents pre-register hypotheses, work reproducibly, and verify before they claim. Pre-registration over TDD.
A practical look at how K-Dense Web can help researchers synthesize hantavirus literature, surveillance, ecology, and public health evidence.
K-Dense Web analyzed 116 declassified UAP files in one prompt, producing a 60-page report separating aerial activity from extraterrestrial evidence.
K-Dense Web ROI audit across 67 public use cases: $3.08M of analyst work delivered by K-Dense Web plus a human for $5,670 in credits.
K-Dense Web synthesizes literature, finds research gaps, and generates a 26-page PhD proposal on biologically inspired robot actuators in about 45 minutes.
ARPA-H policy analysis: K-Dense Web produced a 42-page report with 14 figures, 71 verified citations, and 7 evidence-based recommendations in one session.
K-Dense Web delivers a 7-step due diligence on Structure Therapeutics' GSBR-1290, an oral GLP-1 agonist targeting a $6.5B peak revenue obesity opportunity.
Why we put the hyphen in front of every product we build. The case, from Benchling to AlphaFold to Polanyi, for keeping the human scientist front and center.
K-Dense is evaluating Nemotron 3 Nano Omni — NVIDIA's new open omni-modal model that unifies vision, audio, and language for — agentic scientific workflows.
Pantheon is a free K-Dense app that sends one research question to 80 AI personas, streaming diverse perspectives with cited sources and consensus.
mimeo distills how great minds like Jobs, Buffett, and Wittgenstein reason into a SKILL.md or AGENTS.md your agent can load, with 80+ experts ready today.
Skills are executable research code with a personality. A practical guide to prompt-injection risks, poisoned SKILL.md files, auditing, and version pinning.
Pair NVIDIA OpenShell's policy-governed runtime with Scientific Agent Skills to run autonomous research agents that are highly capable and genuinely safe.
K-Dense Web queried 4 databases and ran 7 Python scripts to produce a 44-page competitive intelligence report on CT-388, Roche's GLP-1/GIP obesity agonist.
K-Dense Web integrated 6 databases, ranked 6 candidate biomarkers, and produced Phase III trial design recommendations for CD20xCD3 bispecifics in DLBCL.
K-Dense Web queried 6 databases, modeled KRAS structure, mapped the tumor microenvironment, and built a 36-slide iNeST strategy for PDAC neoantigen vaccines.
The optimize-for-gpu skill rewrites CPU-bound Python for NVIDIA GPUs across 12 libraries in data science, ML, and simulation, with 58x average speedup.
K-Dense Web scored 45/50 on BixBench-Verified-50, a cleaned biology-agent benchmark designed to separate real model mistakes from benchmark noise.
K-Dense Web automates VC due diligence with research, financial modeling, and publication-ready reports, with CoreWeave ($19B) and Ramp ($32B) case studies.
K-Dense Web vs OpenAI Prism: Prism helps you write papers, while K-Dense Web does the research. See why the distinction matters and how to use them together.
K-Dense is an agentic AI co-scientist platform that turns slow, sequential translational research into an integrated, insight-driven drug development engine.
How K-Dense Web autonomously processed the COCONUT database to identify 50 prioritized antimicrobial candidates using unsupervised machine learning.
K-Dense Web autonomously analyzed 10,000 ICD failure reports from the FDA MAUDE database using NLP and statistics, revealing manufacturer-specific patterns.
Agent Skills close the gap between raw AI intelligence and domain expertise, adding 140 open-source capabilities to AI scientific research workflows.
Write effective prompts for K-Dense Web. Six key elements turn vague requests into precisely executed tasks with publication-ready outputs.
A detailed comparison of K-Dense Web and ChatGPT showing why autonomous task execution beats conversational AI for any complex work.
K-Dense Web is a multi-agent system orchestrating Opus 4.5, Gemini 3 Pro, and Claude Code on a high-compute backend for complex end-to-end workflows.
K-Dense Web vs Scientific Agent Skills: our open-source skills give researchers AI tools; K-Dense Web adds more skills, agents, cloud compute, and zero setup.
How K-Dense Web automates the machine learning workflow, from data prep to model selection and deployment-ready results.
Claude Scientific Writer is a free, open-source tool combining deep research with publication-ready papers, grants, posters, and clinical reports.
Karpathy is our open-source AI agent that trains state-of-the-art ML models autonomously, from data preprocessing to hyperparameter optimization.
Learn how K-Dense Web transforms complex research tasks into automated workflows, delivering publication-ready results across science, finance, and engineering.
