Nexus is GA. Enterprise knowledge, compiled once, query-ready for agents. On Sierra's τ-Knowledge: GPT-5.2 +12% accuracy, -80% cost. GPT-5.5 same accuracy, -77% cost.
Read the full announcement: pinecone.io/blog/pinecone-…
Knowledge is rather abstract and philosophical. So what does it mean from an agentic context? How does providing the right knowledge at the right time to an agent increase its accuracy, task completion, and cost efficiency far above and beyond a frontier model alone? Watch the
Building Agent Skills and testing them is hard, but it doesn't have to be.
Listen to Arjun Patel demo Cultivar, an open source tool developed at Pinecone to help benchmark agent skills in sandboxes. Thanks to @Voxel51 for hosting us!
One dataset. Three totally different questions. Zero retrieval code.
Arjun Patel, senior DevRel at Pinecone, gave Pinecone Nexus a pile of recipes and asked it to organize itself to:
- match his cravings to recipes
- align his shopping list to recipes to make
- combine the above
Most enterprises aren't struggling to scale AI because of the models. They're struggling to get those models to the right knowledge.
Hear more from our PM, Jasmeet, on why we built Pinecone Nexus