I'm excited to share our recent work on the Virtual Lab, a collaboration between human researchers and LLM agents for science research. We apply the Virtual Lab to design nanobody binders for recent variants of SARS-CoV-2 with experimental validation. biorxiv.org/content/10.110…

Super exciting milestone 🎊 The Contextual AI Platform is now generally available for companies that want to build high-quality and production-ready RAG agents. We've been working with major companies like Qualcomm and HSBC to battle-test it, and it's now available more broadly.

Should you use RAG or fine-tuning for your AI use case? 🤔 You need both! Our latest blog shows how combining RAG with specialization techniques like fine-tuning, prompt engineering, and hyperparameter adjustments leads to superior performance compared to RAG-only systems.

Very exciting results

Tired of seeing O3 hallucinate? 😵‍💫 Today, I am excited to share how we built the least hallucinatory LLM in the 🌍 Our GLMv2, developed at Contextual AI, just claimed 1st place 🥇 on the FACTS Grounded leaderboard by Google DeepMind — outperforming Gemini-2.5-pro, Claude 4, and

🔗 You can now connect and sync data directly from enterprise data sources without custom development New connectors for Google Drive & SharePoint are live (Box, OneDrive, Dropbox, Confluence, Salesforce + more coming soon) 🤝 Access data stored in enterprise systems without

Incredibly excited to share the launch of our Data Connectors!! You can now seamlessly bring in your data from third-party sources — complete with entitlements enforcement, auto syncing, and fine grained control over what docs you sync.

Precision. Power. Possibility. A feature from Contextual AI that scales without limits — truly enterprise-grade, built for every unique challenge. In addition to its features, the engineering perfection is also remarkably impressive. Go try it out!!