Workflow
Knowledge Graph
icon
Search documents
AI on Your Lakehouse: Context Comes in Shapes, Not Queries — Zach Blumenfeld, Neo4j
AI Engineer· 2026-07-23 07:00
Hello everyone. Welcome today to get started on AIE. Um, so right here, uh, there's some steps for getting started.I went over this around 10 minutes ago. Um, but basically our workshop that we're going to take today is driven by a website called Graph Academy. And if you go to that first QR code there to the left, uh, that'll take you there.You have to enroll with your email. Um, and then if you go down to set up your environment, uh, there's a code spaces there with everything set up and you can get that ...
Why We Killed Our Multi-Agent Pipeline — Subbiah Sethuraman and Abhilash Asokan, ZS Associates
AI Engineer· 2026-07-23 05:00
System Architecture & Workflow Optimization - Separation of deterministic data processing from agentic systems, using statistical methods, guard rails, and thresholds for automated signal detection prior to agent execution [10][11][25] - Consolidation of the core reasoning process into a single primary agent that retains end-to-end ownership, while allowing dynamic launching of sub-agents solely for focused investigation tasks [12][13][26] - Adoption of a lighter architecture derived from observing cloud code operations rather than strictly mimicking human analyst behavior [9][13][25] Domain Knowledge & Knowledge Graph Integration - Construction of a comprehensive knowledge graph mapping out pharmaceutical commercial domains, including geographic entities, payers, accounts, brands, and hierarchical KPIs [16][17] - Utilization of the knowledge graph as a control plane rather than a simple lookup layer, where every graph edge represents a testable hypothesis to bound and guide agent investigation [18][19][21][26] Business Performance & Operational Efficiency - Identification of specific commercial scenarios where a brand's total prescriptions (TRX) drop by 18% over a 4-week timeframe due to insurance coverage shifts to lower tiers [2][3][19] - Significant reduction in analysis turnaround time, enabling the completion of complex analytical tasks in 20 to 30 minutes compared to the traditional 3 to 4 weeks [24]
Your Moat Is Your Data Model — Mike Phipps, Gates Foundation
AI Engineer· 2026-07-22 21:30
[music] Yes. So my talk today is about the title your data models remote. We have a enterprisewide platform that we had just rolled out here this past month.And so I'll go into details on this. I'll give you some hopefully some practical lessons here and why we made decisions we made for this uh how how you could picture your processes within a similar type framework. So first just a quick introduction.So this gets into the the title here the talk and the the framing of you know what I hope you take from th ...