Pinecone

What happens when the primary users of AI aren't humans, but agents? This week: A new language, new engine, new marketplace, new economics, and new reach. The agentic era needs its own infrastructure category. Our CEO @ashashutosh Founder @EdoLiberty on what it is and what comes next. With perspectives from @Box, @llama_index, @LangChain, @Teradata, @ThoughtFocusTec, and @UnstructuredIO. pinecone.io/blog/knowledge…

Congratulations to @ashashutosh, @EdoLiberty, and the @pinecone team on the launch of Nexus, a knowledge engine for agents. They’ve spent years building at the core of AI infrastructure, and Nexus reflects Pinecone’s point of view on where things are heading, toward systems that

@jennapederson @RoieSchwabco You can also watch over on: 📺 YouTube: @pinecone-io/live" target="_blank" rel="nofollow noopener">youtube.com/@pinecone-io/l… 💼 LinkedIn: linkedin.com/events/7455364…

Agents are now the primary consumers of knowledge infrastructure. Tomorrow @jennapederson, Arjun Patel, and @RoieSchwabco are going live here to talk about what that means for your stack, share this week's Pinecone announcements, and take your questions live. Tuesday May 5 · 11:30am PT / 2:30pm ET / 6:30pm GMT

RT @Box: We’re excited to be part of the @pinecone Nexus launch! For AI agents to actually work in the enterprise, they need context from…

Introducing Pinecone Nexus. A knowledge engine for agents. The bottleneck for production agents isn't the model. It's the per-query work of searching, stitching, parsing tables, normalizing labels. Nexus compiles that work ahead of time into typed, governed artifacts. Agents query through KnowQL. 90% fewer tokens. >90% task completion. 30x faster. Early access open. pinecone.io/blog/introduci…

A million-token context window is not a strategy. 🛑 Our Head of DevRel, @RoieSchwabco , explains why dumping data is killing your RAG performance: 📍 One needle in a haystack? Easy. 📍 Multiple needles? LLMs still fail. 📉 "Lost in the Middle" is a real, measurable problem. "You can't just throw everything onto the vector database without thinking about the meta layer." 🧠 Stop relying on the model to sort it out. Build a meta-knowledge layer to help your agents navigate. 🛠️ Full @ai_rebels episode: youtu.be/gXHF8-ngFYY?si…

Something's coming. Launch week May 4.

Your search is failing because it's looking at words, not meaning. 🛑 Will Templeton, CTO and co-founder at Allspice, explains the "Synonym Trap": ❌ User says "Boston Butt" ❌ DB says "Pork Shoulder" ❌ Result: No match. How Allspice fixed "messy" data with Pinecone: "Instead of storing text and matching against text, you're storing a whole bunch of numbers that represent the meaning. That vector database matches up and you get your result." 🔢🎯 Stop fighting regex and keywords. Shift to vector search. 🛠️ 📺Full breakdown on The Spoon Podcast: youtu.be/TeNWlU4L2Ss?si… 📖 Case study: pinecone.io/customers/alls…

Confidently wrong is worse than just wrong. When an AI searches one giant knowledge base for everything, it finds something—and serves it up like it's the answer. That's not a model problem. That's a knowledge architecture problem. Next week, @jennapederson and @RoieSchwabco are running a hands-on session with @DataCamp showing you how to build an n8n workflow that routes queries to the right knowledge base automatically—so your AI stops guessing and starts actually knowing. This pattern applies anywhere you have different users or steps in a workflow that need different context. → Wednesday, April 29, 11 AM ET → Register: datacamp.com/webinars/build…

Don't burn tokens on search. 📉🔥 Will Templeton, CTO and co-founder at Allspice, explains why they don't let LLMs search their 10,000+ ingredient database: ❌ Searching 10k items in a prompt = waste of time & money. ✅ Vector Search (Pinecone) finds the Top 5 in ms. 🧠 LLM parses the results for "modifiers" & "quantity." "Vector search is the enabling piece. It takes 10,000 ingredients and says: 'These are the five that are closest.'" 🎯 Build for efficiency. Use the right tool for the job. 🛠️ 📺Full breakdown on The Spoon Podcast: youtu.be/TeNWlU4L2Ss?si… 📖 Case study: pinecone.io/customers/alls…

Building AI in New York? Pinecone + The Gen Academy are hosting a meetup in NYC. Panel on real-world AI systems. Raffle. Food. Engineers actually shipping things. No pitch decks. No fluff. High signal. New York City | Doors open 11 AM luma.com/tm4v84ij

Come build with Pinecone x.com/i/broadcasts/1…

File upsert is now live in Pinecone Assistant. Create or replace files by a custom ID you define — no UUID tracking. Upload, upsert, and delete return a pollable operation object. List and describe file operations directly from Assistant. #upsert-a-file" target="_blank" rel="nofollow noopener">docs.pinecone.io/guides/assista…

You can also watch over on: 📺 YouTube: @pinecone-io/live" target="_blank" rel="nofollow noopener">youtube.com/@pinecone-io/l… 💼 LinkedIn: linkedin.com/events/7445867…

🔴 We're going live tomorrow for another Come Build with Pinecone session! Join us to build, break, and learn together. Each session, we pick up a real project — building RAG pipelines, wiring up agents, building semantic search, or exploring what's possible with tools like Claude Code, Cursor, Gemini CLI, or n8n — and work through it live. We talk concepts, hit real challenges, find solutions, and take questions from chat as we go. Join @jennapederson, Arjun Patel, and @RoieSchwabco to build, chat, and get your questions answered live. You can find us right here: 🗓️ Wednesday, April 22, 2026 ⏰ 10am PT / 1pm ET / 5pm GMT 🐦 @pinecone Drop your questions in the replies or bring them to the stream.

The "bridge of authority" in RAG: ❌ LLMs can reason about "blue skies" or "purple skies" with the same authority. ✅ Vector DBs let you peer into the metadata to find the source/author. "Do you trust a thing because an AI said so? Or because there's a trace that tells you where the claim comes from?" 🛡️ -- Pinecone Head of DevRel @RoieSchwabco Stop relying on training data vibes. Build traceable, grounded apps. 🛠️ Full @ai_rebels episode: youtu.be/gXHF8-ngFYY?si…

Building AI in the Bay Area? Pinecone + The Gen Academy are hosting a meetup at Menlo Ventures. Panel on real-world AI systems. Raffle. Food. Engineers actually shipping things. No pitch decks. No fluff. High signal. Menlo Ventures, SF | Doors open 5 PM luma.com/5lms9659