Pinecone 2.0
Edo Liberty
- When
- Tuesday, June 3010:45 AM – 11:05 AM · 20 min
- Where
- Track 3San Francisco, CA · imported from ai.engineer's public schedule feed
About this session
Autonomous agents are smart but don’t know your business or your objectives. That’s why most agents in the enterprise remain stuck in retrieval loops, burning millions of tokens on processing raw documents
A shift from traditional retrieval systems + agents (aka RAG) to purpose-built knowledge engines is underway.
I'll talk about why moving reasoning upstream and compiling raw enterprise data into specialized, task-specific context artifacts is critical to unlocking reliable agentic workflows. And I'll show you how offloading knowledge management to a dedicated layer enables engineering teams to achieve up to a 90% reduction in token consumption while drastically improving task completion rates, speed, and accuracy.
Speaker
Founder and Chief Scientist, Pinecone
Edo Liberty is the founder and Chief Scientist of Pinecone. Pinecone is the knowledge infrastructure for AI at scale. Its leading vector database and knowledge engine, Pinecone Nexus, power accurate, performant AI applications for more than 10,000 customers and 1M developers worldwide. Before founding Pinecone, Edo was a Director of Research at AWS and Head of Amazon AI Labs where his team built cutting-edge machine learning algorithms, systems, and services including parts of Amazon SageMaker and OpenSearch. Edo holds a B.Sc in Physics and Computer Science from Tel Aviv University, and a Ph.D. in Computer Science from Yale. As an academic Edo taught at Tel Aviv University and at Princeton and has authored more than 75 papers and patents. His research focused on mathematical foundations of AI, optimization, streaming algorithms, machine learning, numerical linear algebra, and high dimensional data mining.
More in Search & Retrieval
- The unreasonable effectiveness of BM25 for agentic searchTuesday, June 30 · 11:10 AM – 11:30 AM · Track 3
- The Search Engine for the Agentic WebTuesday, June 30 · 11:40 AM – 12:00 PM · Track 3
- Rebuilding the web for agentsTuesday, June 30 · 12:05 PM – 12:25 PM · Track 3
- If we want them to do Knowledge Work, we need to design Knowledge AgentsTuesday, June 30 · 1:30 PM – 1:50 PM · Track 3
- Your Agreements Are a Database You Can't Query. We're Fixing ThatTuesday, June 30 · 1:55 PM – 2:15 PM · Track 3
For developers: this programme is open data — JSON, iCal, schedule XML and an MCP endpoint.Show endpointsHide
- JSONEvery published session and speaker, in one request./aie-worldsfair-2026-import/feed.json
- iCalSubscribe in Google, Apple or Outlook Calendar./aie-worldsfair-2026-import/feed.ics
- Schedule XMLfrab / pentabarf — the format conference apps import./aie-worldsfair-2026-import/feed.xml
- MCP + RESTPoint Claude at the programme. OpenAPI 3.1 included./agents
No key, no signup, CORS open. Everything here is generated from the same data the organisers edit.