Tim Graciano

A thoughtful piece by our own Brian de Luna on Applied Science in marketplaces, and the unique journey we’ve taken at Faire.

17

Just read a compelling article from my colleague Noel McMichael that nails an AI problem I've been thinking about a lot lately. As we move toward deploying autonomous, API-using agents, we're hitting a wall. These agents are active and adaptive, yet they often lack a verifiable identity, a complete audit trail, or clear revocation logic. This makes them a black box, which creates risk for companies of all sizes and scopes. Noel warns that the biggest risk isn't only technical... it's "institutional paralysis". Companies that can't verify their AI's behavior will refuse to deploy them for anything important. This will likely create a two-tier system where only organizations with resources to build custom solutions benefit from AI, while everyone else operates in an environment of mistrust. His solution is a "trust fabric for AI", which is essentially a unified layer that sits below the application and above the model. This fabric would bring together the technical primitives that already exist, like persistent identity, scoped permission sets, verifiable provenance, and credential chains, to make agent behavior verifiable and secure. I really like Noel's take and highly recommend reading the full article (link in the comments section) #AI #AgenticAI #Trust #DataGovernance #AIEthics

21

2 Comments

Truly transformative. Within the next 6 months coding will be fully commoditized. Only design, distribution, and hardware will be the moat. It is time to lean in #AI #FutureofWork #OhioTech

1

1 Comment

The goal of Machine Learning University (MLU) is to "enable Amazonians to identify ML and generative AI problems, have productive conversations about ML and generative AI projects, and get ML and generative AI models into production faster." I highly recommend the ML for Leaders Generative AI course to my fellow Amazonians.

50

5 Comments

Excited to share how Wayfair is leveraging OpenAI to transform their e-commerce operations! Rather than treating generative AI as just a side experiment, Wayfair has successfully embedded OpenAI models into their core internal workflows—and the results speak for themselves. Here is how they are driving measurable impact at scale: Catalog Accuracy & SEO Boost: Wayfair transitioned from using expensive, bespoke models to a scalable, tag-agnostic AI architecture. They have already corrected 2.5 million product tags across over a million highly-visible products, leading to a significant increase in SEO performance, clicks, and customer discovery. Meet "Wilma": To handle complex supplier support requests, Wayfair introduced agentic AI workflows. Wilma automates ticket triage, fills in missing context, and suggests draft responses. The result? They are now automating 41,000 tickets per month (up to 70% in some workflows!), drastically reducing manual work and turnaround times. Empowering the Workforce: Beyond operational workflows, Wayfair has deployed over 1,200 ChatGPT Enterprise seats to help their 12,000-person team problem-solve, experiment, and move faster every day. It’s a fantastic masterclass in using AI to not only augment human expertise but also build a better, more trusted shopping journey for customers. Read the full case study here: https://lnkd.in/gyUPsV7s

29

A couple of months ago I took Tim Januschowski's Modern Forecasting in Practice course on Maven. Tim led the time series science organization at AWS AI, where his teams built SageMaker Forecast and other AWS forecasting services. One idea from the course kept pulling at me: foundation models that forecast diverse time series with zero domain-specific tuning. No feature engineering. No custom architecture. I kept thinking: this solves the problem every MMM practitioner runs into. We build causal models that explain sales well. Adstock effects, saturation curves, channel-level ROI. Then someone asks: what happens next quarter if we shift budget from TV to search? And the model can't answer, because it needs future employment rates and temperature data. Values that don't exist yet. Most teams handle this with naive estimates or by dropping controls entirely. Both options undermine the model they spent months calibrating. So I put together a proof of concept to test whether foundation models could close that gap. The idea: train an MMM on historical data, use Chronos2 to forecast the control variables, then feed those forecasts into the MMM for scenario planning. In our simulation, the added prediction error from using forecasted controls instead of actuals was minimal. The error propagation math also turned out to be straightforward, which means practitioners can estimate upfront whether their control forecasts are accurate enough to be useful. So it's not causal models versus foundation models. MMMs encode what causes what. Foundation models predict what hasn't happened yet. Combine them and you get a causally grounded scenario planning system with quantified uncertainty on the key assumptions. Full methodology, reproducible notebook, and results in our new blog post: https://lnkd.in/ee3gVHxW And if you want to go deep on modern forecasting, highly recommend Tim's course: https://lnkd.in/ezZQ4uhU

28

2 Comments

🚀 Just wrapped up a hands-on project applying Retrieval-Augmented Generation (RAG) to a real-world use case: interpreting LIC’s New Jeevan Shanti policy document using LLMs. The core idea? Combine vector search over regulatory PDFs with GPT-4 to generate grounded, faithful answers to complex policy questions. Key capabilities we built: ✅ LCEL-based RAG architecture using LangChain ✅ Contextual compression retriever for focused document lookup ✅ Modular LLM & embedding selection (OpenAI, HuggingFace, Mistral) ✅ Evaluation using LLM-powered metrics: faithfulness, relevance, correctness 📄 The document used is publicly available here: LIC New Jeevan Shanti Policy PDF 💻 Full code available on GitHub: https://lnkd.in/gS9mEzWA 💡 This architecture brings the best of both worlds — retrieval accuracy and generative flexibility — especially in regulated domains like insurance and financial services. 🔜 Next step: Incorporate Agents that can reason across multiple steps — not just answer a question, but decide which tools to use, when to search, how to validate, and when to stop. That’s where the future of enterprise GenAI lies. Would love to hear how others are pushing RAG, agents, and LLMs in production! #GenAI #LangChain #LLM #RAG #AIForOps #InsuranceTech #LLMEvaluation #LangChainAgents

61

1 Comment

An interesting approach to the multi-turn chart editing task. LLM-supported editing of complex artifacts will be one of the major applications of LLMs, embedded within broader consumer and business workflows. As a result, evaluation methods for these types of interactive, multi-step editing tasks will become increasingly important and widely adopted. https://lnkd.in/gThNvenR

10