Data Science Dojo✓

The July 14th cohort is coming up soon. 10 weeks. 12,000+ alumni. Spots are filling fast. The Agentic AI Bootcamp is back and it covers the full stack of what matters right now. Week 1, you're wrapping your head around how Transformers actually work. Week 3, you're building with LangChain and setting up your first vector database for a RAG pipeline. By week 5, you're not just prompting. You're engineering context and designing systems using Agentic design patterns used in production. Week 7 hits and you're implementing Model Context Protocol and learning how agents actually talk to each other. Week 10? You ship a multi-agent LLM application. From scratch. In 10 weeks. That's what the Agentic AI Bootcamp cohort starting July 14th looks like. 3 hours a week, structured to take you from foundations to deployment. Register now before it's too late: #agenticai #rag #aibootcamp #vectordatabases

We’re excited to welcome Allison Ding, Senior Developer Advocate at NVIDIA, to the Agentic AI Conference! 🎙️ Allison will be leading the hands-on tutorial “Teaching Coding Agents to Think in GPU: Writing, Testing, and Shipping Agentic Skills.” Ask a coding agent to speed up a slow pandas job and you often get pandas back: correct, confident, and still on the CPU. In this session, you’ll learn how to fix that with agentic skills, plain markdown files that route an agent to the right library, ground it in the current docs, and validate its work at runtime. You’ll take apart a real production skill for NVIDIA CUDA-X Data Science, write one together, and leave with a working skill and a repeatable way to prove it works. At NVIDIA, Allison is a senior developer advocate and technical marketing engineer who helps developers get more out of GPU-accelerated AI libraries and tools, with a focus on accelerated data science and large language models. She teaches through hands-on workshops, talks, live demos, livestreams, and YouTube videos, and with more than a decade of industry experience, she enjoys turning complex tech into something you can try in an afternoon. 📅 November 9–10, 2026 | Virtual | Free to attend 🔗 Register now to save your spot: #datasciencedojo #agenticaiconference #futureofdataandai

One keynote. Six panels. Four hands-on tutorials. 🎙️ The people building AI agents at Docker, Google DeepMind, Databricks, Atlassian, AMD, Neo4j, Cohere, and more are coming together for two days on security, compliance, governance, and alignment. Swipe to meet every session and the speakers leading it. 👉 📅 November 9–10, 2026 | 9 AM – 3 PM PT | Virtual | Free to attend 🔗 Register free: #datasciencedojo #agenticaiconference #futureofdataandai

Four people who build and run AI products are joining the panel “Teammates, Not Tools” at the Agentic AI Conference: Raja Iqbal (Founder, Ejento AI), Sam Partee (Co-founder and CTO, Arcade), Adnan Ijaz (Senior Director of Product Management, Google) and Jamil Valliani (Head of Product, AI, Atlassian). 🎙️ AI agents can now act on their own, moving money, rewriting customer records, and touching production systems. That makes them less like software and more like new team members, and team members need a role, an identity, a manager, and limits on what they can decide alone. Most organizations haven’t given their agents any of that yet. Built on the Harvard Business Review article “To Scale AI Agents Successfully, Think of Them Like Team Members,” this panel will look at what onboarding an agent really involves, from scoped credentials to sign-off thresholds and audit trails. Our panelists will also take on the question every leader faces: how much should an agent be trusted with from the start, and how does it earn more? 📅 November 9–10, 2026 | 9 AM – 3 PM PT | Virtual | Free to attend 🔗 Register now to save your spot: #datasciencedojo #agenticaiconference #futureofdataandai

We’re excited to welcome Jamil Valliani, Head of Product, AI at Atlassian, to the Agentic AI Conference! 🎙️ Jamil will be joining the panel “Teammates, Not Tools.” How much authority should a digital teammate get on day one, and what must it prove to earn more? Expect a candid conversation about per-agent identity, who answers when an agent acts, and where a human still signs off. Jamil leads product for AI at Atlassian, where the focus is how teams work with AI. Before that, Jamil spent over 15 years at Microsoft, founding the Services Marketplace business and leading Bing Image Search and Video search, among the first products to use computer vision and deep learning for multimedia search. 📅 November 9–10, 2026 | 9 AM – 3 PM PT | Virtual | Free to attend 🔗 Register now to save your spot: #datasciencedojo #agenticaiconference #futureofdataandai

Four hands-on tutorials, four things you’ll build. 🛠️ 1️⃣ Neo4j: a data agent you can audit 2️⃣ AMD: a local agent that works your inbox inside limits you set 3️⃣ Google DeepMind: prototype to production, with live demos 4️⃣ LandingAI: document version control where every word is cited Swipe to see what each one covers and who is teaching it. 📅 November 9–10, 2026 | 9 AM – 3 PM PT | Virtual | Free to attend 🔗 Register free: #datasciencedojo #agenticaiconference #futureofdataandai

Every company has documents. Can an AI platform be trusted to read them for you? 📄 Join Jaya Vivekanandan, Applied AI Engineer at LandingAI, for the hands-on tutorial “Show Me Where It Says That: Agents That Cite Every Word in a Document” at the Agentic AI Conference. You’ll work with DPT-3 Verity, the newest parsing model in LandingAI’s Agentic Document Extraction, which grounds every word it reads, in text and in tables, to its exact spot on the page and gives it a confidence score. What you’ll build: ✅ Highlight and cite the exact phrase on the page ✅ Route low-confidence content to a person while the rest flows straight through ✅ Verify each extracted value against the words it came from ✅ A document version-control pipeline that finds every addition, removal, and edit across lease revisions, with no false changes from layout Along the way, you’ll learn why a low confidence score means “check this,” not “this is wrong.” You’ll leave with working code and a practical sense of where Verity fits in your own pipelines. Swipe through for the details. 👉 📅 November 9–10, 2026 | 9 AM – 3 PM PT | Virtual | Free to attend 🔗 Register now to save your spot: #datasciencedojo #agenticaiconference #futureofdataandai

The attack is already in your index. 🔐 In 2025, researchers embedded instructions in an ordinary web form and watched an agent retrieve sensitive CRM records and send them to an external address. Nothing about the model was compromised. The payload arrived the way every other piece of context arrives, through a field a customer is supposed to fill in. We’re excited to have Scott Askinosie (Principal AI Architect, Knowledge & Memory Systems, SteelEngine), James Luan (CTO, Zilliz), and Kiran Bondalapati (Engineering Leader, Glean) joining the panel “The Attack Is Already in Your Index” at the Agentic AI Conference. As agents pull from retrieved documents, tool responses, and memory, that content becomes something they act on, and most security reviews still don’t treat it that way. The panelists will cover what teams are actually putting in place: provenance tracking that traces an action back to the document that triggered it, validation of external inputs before an agent acts on them, and detection that works on content nobody wrote by hand. Expect a real debate: can poisoned context be reliably caught and cleaned, or is the only durable answer keeping untrusted content away from anything privileged? Swipe through for the full story. 👉 📅 November 9–10, 2026 | 9 AM – 3 PM PT | Virtual | Free to attend 🔗 Register now to save your spot: #datasciencedojo #agenticaiconference #futureofdataandai

guidance.pdf → deployment: stalled 🔐 A vendor’s security guidance assumes a reference architecture nobody actually runs. A compliance framework assumes clean data ownership and a documented approval chain. Red-teaming findings assume somebody on the receiving end knows what to do with them. Every organization receiving them has its own legacy systems, risk appetite, and way of deciding things, and the distance between the guidance and the deployment is where AI programs stall. We’re excited to have Aater Suleman (Co-founder, Vixul), Hannah Marlowe (Senior Director, AI Forward Deployed Engineering, Databricks), and Dan Maloney (CEO, LandingAI) joining the panel “Secure AI Needs Forward Deployed Engineers” at the Agentic AI Conference. They’ll dig into how forward deployed engineers close that distance, turning guardrails, threat models, and control requirements into integrations that fit how a real enterprise runs, and whether that work can scale beyond one customer at a time. Then comes the disagreement: is the FDE a permanent fixture of enterprise AI, or a sign the tooling simply isn’t finished? Swipe through for the full story. 👉 📅 November 9–10, 2026 | 9 AM – 3 PM PT | Virtual | Free to attend 🔗 Register now to save your spot: #datasciencedojo #agenticaiconference #futureofdataandai

Four AI educators. Co-founders and instructors at Now on one panel at the Agentic AI Conference. Luis Serrano (Serrano Academy), Chris McCormick, Jay Alammar (Cohere), and Josh Starmer (StatQuest) are joining the panel “How Do Agents Work, and How Should They?” The RAG Pack began with a course idea from Luis that the others wanted to build together, and today they teach Reinforcement Learning for LLMs, Introduction to Agents, and the free masterclass Why Do We Need Agents? Their approach is intuition first, with visuals, code, and formulas side by side. The panel has two open issues: #1 How do agents work? #2 And how should they work? All four take both on, together, in one 45-minute panel. If you’ve learned from Grokking Machine Learning, Hands-On Large Language Models, An Illustrated Guide to AI Agents, the StatQuest Illustrated Guides, or Chris’s deep-dive tutorials on BERT and transformers, this is your chance to hear their authors live. Swipe through to meet the contributors. 👉 📅 November 9–10, 2026 | 9 AM – 3 PM PT | Virtual | Free to attend 🔗 Register now to save your spot: #datasciencedojo #agenticaiconference #futureofdataandai

sandbox: airtight: true, except… 🔐 Every sandbox ends up with exceptions. An agent that can file a ticket is useful. One that can also close it, refund the customer, and push a config change is considerably more useful, and now has enough reach to do real damage through a bug, a bad instruction, or a prompt it should never have trusted. And telling an agent not to do something is not the same as preventing it. We’re excited to have Suman Debnath (Director of Developer Relations Engineering, Crusoe), Ori Bendet (VP of Product, Docker), and Dwayne McDaniel (Principal Developer Advocate, GitGuardian) joining the panel “Every Sandbox Ends Up with Exceptions” at the Agentic AI Conference. They’ll dig into what teams have actually shipped, from container-level isolation and scoped credentials to network egress rules and approval gates on destructive operations, and the failure modes that shaped them. Then comes the disagreement: does a well-designed sandbox genuinely contain an agent, or does every production deployment accumulate exceptions until the boundary is mostly decorative? Swipe through for the full story. 👉 📅 November 9–10, 2026 | 9 AM – 3 PM PT | Virtual | Free to attend 🔗 Register now to save your spot: #datasciencedojo #agenticaiconference #futureofdataandai

An always-on agent is only worth having if you can trust it. 🔐 Join Iswarya Alex and Satya Devineni from AMD for the hands-on tutorial “Build Secure Always-On Local Agents on AMD Ryzen™ AI PC using Lemonade” at the Agentic AI Conference. Instead of assuming trust, this session starts from it and builds the agent around it, limit by limit. Here’s what you’ll build: ✅ An agent that runs day and night, working on your actual inbox and calendar ✅ Fully local inference, with Lemonade Server keeping every model call on the machine across the NPU and GPU ✅ A sandbox where what the agent can read, run, and reach is a policy you write and can change ✅ A fun productivity use case, hands-on and end to end Everything is provided: an AMD Ryzen™ AI PC, a synthetic dataset, and a simulated environment. Swipe through to see how it works. 👉 📅 November 9–10, 2026 | 9 AM – 3 PM PT | Virtual | Free to attend 🔗 Register now to save your spot: #datasciencedojo #agenticaiconference #futureofdataandai

We’re excited to have Scott Askinosie, James Luan, and Kiran Bondalapati joining the panel “The Attack Is Already in Your Index” at the Agentic AI Conference! 🎙️ Scott is Principal AI Architect for Knowledge and Memory Systems at SteelEngine. James is the CTO of Zilliz, Chair of the Milvus community, and a member of the LF AI & Data Foundation’s Technical Advisory Committee. Kiran is an Engineering Leader at Glean, building enterprise AI systems with trusted context, permissions, and agentic workflows, and was previously VP of Engineering at TRM Labs. In 2025, researchers embedded instructions in an ordinary web form and watched an agent retrieve sensitive CRM records and send them to an external address. Nothing about the model was compromised: the payload arrived the way all context does. As agents pull from documents, tool responses, and memory, that content becomes executable in a way most security reviews still don’t treat it. This panel covers what teams are actually putting in place: provenance tracking, validation of external inputs, and detection for content nobody wrote by hand. Expect a real debate on whether poisoned context can be reliably caught and cleaned, or whether the only durable answer is keeping untrusted content away from anything privileged. 📅 November 9–10, 2026 | 9 AM – 3 PM PT | Virtual | Free to attend 🔗 Register now to save your spot: #datasciencedojo #agenticaiconference #futureofdataandai

We’re excited to welcome Kiran Bondalapati, Engineering Leader at Glean, to the Agentic AI Conference! 🎙️ Kiran will be joining the panel “The Attack Is Already in Your Index.” As AI systems pull from documents, tool responses, and memory stores, that content becomes something an agent can act on, in a way most security reviews still don’t account for. This panel will treat poisoned context as a present-day audit question, not a future threat, and look at what teams are doing about it, from tracing actions back to their source to keeping untrusted content away from anything privileged. At Glean, Kiran works alongside software, data, machine learning, AI, security, and legal professionals to build enterprise AI systems, from trusted context and permissions to agentic workflows and the infrastructure behind them. With more than 20 years in the technology industry, Kiran was previously VP of Engineering at TRM Labs, the blockchain intelligence company, and earlier worked on Uber’s compute infrastructure and on micro-virtualization at Bromium. 📅 November 9–10, 2026 | Virtual | Free to attend 🔗 Register now to save your spot: #datasciencedojo #agenticaiconference #futureofdataandai

Missed it live? The recording of Part 3 of our SambaNova coding agent series is now up 🎥 In “Give Your Coding Agent a Real Workspace: Tools, Tests, Git & MCP,” Kwasi Ankomah, Lead AI Architect at SambaNova Systems, covered: 🛠️ Giving a coding agent a real workspace: files, code execution, tests and Git 🎯 Designing those tools so the agent uses them reliably 🛡️ Sandboxing the workspace so the agent can act freely without putting your systems at risk 🔌 Extending the agent with developer tools over MCP ✅ The finish line: the agent opening a PR-style diff that passes CI ▶️ Watch the full session: #CodingAgents #AgenticAI #MCP #AIEngineering

How do agents work, and how should they? 🤖 The RAG Pack is coming to the Agentic AI Conference! Luis Serrano, Chris McCormick, Jay Alammar, and Josh Starmer, four AI educators and the co-founders and instructors of come together on one stage to take on both halves of that question. The RAG Pack began with a course idea from Luis that the others wanted to build together. Their courses, including Reinforcement Learning for LLMs and Introduction to Agents, are intuition-first, with visuals, code, and formulas side by side. You probably already know their work: Jay co-authored Hands-On Large Language Models and An Illustrated Guide to AI Agents, Luis wrote Grokking Machine Learning, Josh wrote The StatQuest Illustrated Guides to Machine Learning and to Neural Networks and AI, and Chris’s deep-dive tutorials on BERT, transformers, and NLP are go-to references for practitioners. Now hear all four together, live. Swipe through to meet the Pack. 👉 📅 November 9–10, 2026 | 9 AM – 3 PM PT | Virtual | Free to attend 🔗 Register now to save your spot: #datasciencedojo #agenticaiconference #futureofdataandai

What’s new and what’s next from Google DeepMind? See it live. 🚀 Join Paige Bailey, AI Developer Relations Lead at Google DeepMind, for a first-hand look at the latest models and agentic workflows coming from Google DeepMind at the Agentic AI Conference. What you’ll take away: ✅ Live demos with Gemini 4, NanoBanana 2.1, Gemini TTS, and more ✅ A first-hand look at the agentic workflows coming from Google DeepMind ✅ Hands-on coding patterns for going from prototype to production with next-gen autonomous systems Paige has helped define the developer experience for Gemini, PaLM 2, and Gemma, and presented AI Studio, the Gemini APIs, and new additions to Antigravity in the developer keynotes at Google I/O ‘25 and ‘26. Swipe through for the details. 👉 📅 November 9–10, 2026 | 9 AM – 3 PM PT | Virtual | Free to attend 🔗 Register now to save your spot: #datasciencedojo #agenticaiconference #futureofdataandai

Six panels on what it really takes to trust AI agents in production. 🔐 This year’s Agentic AI Conference brings together leaders from Docker, Google, Databricks, Cohere, Glean, deepset, Together AI, LandingAI, and more for six candid conversations on security, compliance, governance, and alignment: 1️⃣ How Sovereign Is Sovereign AI? What hosting your own weights, data, and compute actually buys 2️⃣ Secure AI Needs Forward Deployed Engineers: Why compliant deployment happens through people embedded in the organization 3️⃣ Teammates, Not Tools: Roles, authority, and accountability for AI agents 4️⃣ How Do Agents Work, and How Should They? The RAG Pack on how AI agents work, and where they fail 5️⃣ Every Sandbox Ends Up with Exceptions: Why isolating agents is straightforward until they need to be useful 6️⃣ The Attack Is Already in Your Index: Why retrieved documents, tool responses, and memory are the softest way in Every panel is built around a real disagreement, so expect honest debate, not a shared script. Swipe through to see each panel and who’s on it. 👉 📅 November 9–10, 2026 | 9 AM – 3 PM PT | Virtual | Free to attend 🔗 Register now to save your spot: #datasciencedojo #agenticaiconference #futureofdataandai

Give Your Coding Agent a Real Workspace: Tools, Tests, Git & MCP

🔴 Happening today at 11:00 AM PT A coding agent that can only plan is a coding agent that can’t ship. Today, Kwasi Ankomah, Lead AI Architect at SambaNova Systems, gives one a real workspace, live: 🛠️ Files, code execution, tests and Git 🎯 Tool design, so the agent uses them reliably 🛡️ A sandbox, so it acts freely without putting your systems at risk 🔌 Developer tools over MCP The payoff: the agent opens a PR-style diff that passes CI. It’s free, it’s virtual, and there’s still time to grab a spot 👇 🔗 #CodingAgents #AgenticAI #MCP #AIEngineering #DevOps

Data agents rarely fail loudly. They return plausible numbers, query data they shouldn’t, and leave no trail you can audit. 🔍 Join Benjamin Squire, Senior Developer Advocate at Neo4j, for the hands-on tutorial “Making a Data Agent Trustworthy with a Semantic Layer and Auditable Memory” at the Agentic AI Conference. You’ll watch one text-to-SQL agent run twice over a realistic 33-table BigQuery warehouse, once with the usual list-tables-and-guess tooling and once with graph-based context from two Neo4j Labs projects. What you’ll learn: ✅ Add a semantic layer of governed metrics, business synonyms, and sensitivity tags, checked before any query runs ✅ Record every reasoning step with auditable agent memory ✅ Answer “who accessed this data, and why?” with a single graph query ✅ Trace a planted prompt injection to its source and quarantine it You’ll leave with a public repo to rerun everything yourself. Swipe through for the details. 👉 📅 November 9–10, 2026 | 9 AM – 3 PM PT | Virtual | Free to attend 🔗 Register now to save your spot: #datasciencedojo #agenticaiconference #futureofdataandai