Get Out of the Model's Way — Kevin Hou, Google Antigravity
아직 글이 준비되지 않았습니다이 영상의 정보는 있지만 글은 아직 작성되지 않았습니다. 그동안 YouTube에서 시청할 수 있습니다.YouTube에서 열기 같은 채널의 다른 글
슬라이드 12장17:56EN
AI Engineer· 2026년 10월 25일How Bridgewater Keeps Its AI Analyst Inside Permission BoundariesNikhil Benesch, Aaron Linsky · turbopufferAaron Linsky and Nikhil Benesch explain why search over an enterprise vault must honor document permissions without sacrificing recall or speed. Their solution combines vector indexing with native filtering to search hundreds of millions of vectors in roughly 120 milliseconds.엔터프라이즈 AIPrivacy & data governanceSearch & retrieval+2
슬라이드 7장35:19ENAI Engineer· 2026년 10월 25일SallyAnn DeLucia: How to Write Your First AI EvalSallyAnn DeLucia · Arize AITurn an agent’s real traces into concrete pass/fail criteria, then build an LLM judge you can test, align with people, and run in production.평가와 관측 가능성평가(Evals)에이전트 엔지니어링+2 
슬라이드 9장20:58ENAI Engineer· 2026년 10월 25일Vinoo Ganesh on Making Financial AI Cite Every NumberVinoo Ganesh · KeplerKepler CEO Vinoo Ganesh explains why financial AI should retrieve and cite figures while deterministic software handles the math. His design makes traceability, retrieval quality, and tenant security part of the answer itself.금융 AI엔터프라이즈 AI검색 증강 생성(RAG)+2 
슬라이드 10장18:31ENAI Engineer· 2026년 10월 25일Janie Gu and Suyeol Yun: Why Frontier Models Fail as Buy-Side AnalystsJanie Gu, Suyeol Yun · Google DeepMindJanie Gu explains why benchmark scores can mislead, while Suyeol Yun presents MandateBench, which tests whether a model can turn a fund mandate into a defensible investment memo. The two talks show why real workflows, reproducible grading, and evidence-backed reasoning matter.금융 AIBenchmarks평가(Evals)+2 
슬라이드 8장15:27ENAI Engineer· 2026년 10월 25일What AI Engineers Do Now: Build the Loop Around AgentsAparna Dhinakaran · Arize AIAparna Dhinakaran argues that AI engineers are moving from shipping individual features to building systems that let agent teams improve them. At Arize, that means tracing agent behavior, evaluating its work against human judgment, and feeding those signals back into an always-on agent.에이전트 엔지니어링평가(Evals)관측 가능성과 안정성+2 
슬라이드 7장19:37ENAI Engineer· 2026년 10월 25일Jay Sahnan and Arik Bird on Building Financial Agents for the Whole WebJay Sahnan, Arik Bird · BrowserbaseBrowserbase’s Jay Sahnan and Arik Bird show how browser agents reach financial data hidden behind logins and bot defenses. Their Ramp, Bill, and Stripe examples connect reliable cloud browsers with Stagehand’s more adaptive controls.에이전트 엔지니어링Computer useWorkflow automation+2