Rashmit Das

Launching: Chat with Priyank (beta) today on https://priyank.tech A few weeks ago, I launched priyank.tech as a single home for my work, projects, and notes. Today I’m adding a faster way to get to the signal: Skip the scrolling, ask.  “Chat with Priyank” answers questions about my projects, views, and skills by pulling the most relevant context and giving you a concise, useful response. What’s under the hood (and why): - Human‑verified access - Conversations start only after the system knows it’s interacting with a person, not a bot. - Scope & guardrails - It only answers questions about me. When a query is out of scope or uncertain, it responds with a polite “I don’t know.” - Context engineering first (no RAG, yet!) - An analysis by industry veterans suggested that GPT-5 class models can correctly use ~85% of the provided context. I want to see how far careful, prompt, and context design can go before adding retrieval. I’ll evaluate this over the next few days and decide before graduating from beta. - Prompt caching enabled - To keep costs under control (and responses snappy), repeat prompts and shared context are cached. - Early memory layer - A lightweight short-term memory layer powers more personal, consistent answers across sessions. Try it on: https://priyank.tech   If it’s your first visit, do subscribe to my newsletter—I’ll share build notes, decisions, and lessons learned there. Starter prompts: “Tell me about your AI and Generative AI expertise “How can you help me become an AI first organization?” Feedback is welcome, especially edge cases and failure modes.  #AI #product #buildinpublic #LLM

31

2 Comments

As we continue to help our customers and partners transform consumer experiences across industry sectors from healthcare to retail to media & entertainment, I am incredibly excited to share the announcement of Google Cloud’s strategic partnership with BRAHMA AI — a pioneering company scaling high-fidelity, interactive “digital humans” for global enterprises. Hear it from CEO Prabhu Narasimhan himself — or rather, from his digital human “ATMAN”.

21

1 Comment

2026 marks the shift from AI experimentation to real-world deployment—where agentic AI solutions tackle complex business problems autonomously with a focus on vertical solutions. AWS's Rishi Bhaskar shares insights with Nextgov on this transformation, emphasizing that success starts with a data-first approach to modernize legacy systems and deliver measurable outcomes. Get the details:

12

How did LangTalks end up meeting with Andrew Ng, Anshul Ramachandran (Windsurf), and Roey Zalta And what book does #LarryPage wish he had when he started Google? It all relates to the question that keeps me up at night: how should our evolving understanding of 'search & retrieval', 'context engineering', and 'evals' shape the way we design systems? And how should we account for these shifting dynamics in the planning stage with a forward looking approach? (Though Page’s recommendation is real, so I hope you read until the end.) First, the new course Agentic AI with Andrew Ng is one of the best resources I’ve found (especially Module 4 on evals) [1]. I also recommend listening to LangTalk’s episode on search & retrieval with Guy Itach [2]. I especially liked the ending, where they show how technical aspects are combined with product sense and domain expertise, and why choosing the right evals isn’t straightforward at all. Don’t miss Roy Zalta’s post [3] on how he achieved 98% accuracy in his RAG system using a combination of eleven different strategies. And last but not least: Windsurf’s AI Coding Agents [4]. Specifically, the section on “Search & Discovery for AI Agents,” where Anshul presents a multi-step retrieval paradigm—that blew my mind (it’s free). Another thought I’ve had on 'evals and error analysis' is that it's somewhat derivative of the OKRs methodology—an incredibly powerful concept for driving clarity, prioritization, organizational alignment, and decision-making. I honestly can’t recommend Measure What Matters [5] enough—but don’t take my word for it. See what Larry Page, Alphabet CEO and Google cofounder, had to say: "I wish I had had this book nineteen years ago, when we founded Google. Or even before that, when I was only managing myself! As much as I hate process, good ideas with great execution are how you make magic. And that’s where OKRs come in." Circling back to my question: As we shift toward agentic systems, how do you see the evolution of system design? What planning strategies are you starting to prioritize from the very beginning?

6

1 Comment

I just read “Enterprise AI’s Reality Check” by Kapil Venkatachalam at FTV Capital, and it's a breath of fresh air amidst the AI hype. Kapil cuts right to it: amid billions in infrastructure bets and LLM growth, the real opportunities lie deeper—at the application layer, where AI directly powers business value. From personalized assistants adding real revenue at companies like Toast, Taco Bell, and Bank of America, to startups like Orbus Software, Windward, Arden Insurance, and Kore.ai, AI is starting to deliver beyond pilot illusions.. If you're focused on bridging the gap between AI experimentation and business outcomes, this is a must-read! #aiforreal #AIAdoption #AIAdoption #AIApplications #DataGovernance #AIInfrastructure #AIAtScale https://lnkd.in/ggzyBexW

3

10 Years at AWS: Lessons from Building at Scale This month marks 10 years since I joined Amazon Web Services (AWS), fresh out of business school. Over the past decade, working across expansion strategy, AI, and global cloud infrastructure at scale, I’ve had a front-row seat to how large, complex systems get built and what makes them endure. A few lessons stand out. 1. Teams build everything. Nothing meaningful at AWS is done alone. Durable systems emerge from diverse teams working across cultures, time zones, and years. AWS Regions are the product of hundreds of teams aligning around a shared outcome well beyond the first delivery milestones. 2. Long-term thinking is a real competitive advantage. The hardest problems take years to solve and create the most customer value when done right. The AWS European Sovereign Cloud is one example, a multi-year effort that only works if you invest patiently before results are visible. 3. At scale, operational excellence compounds trust. Customers don’t experience strategy. They experience availability, latency, security, and reliability every day. I’ve been part of countless services reviews and escalations with one goal: make sure customers have what they need, when they need it. 4. Small mechanisms beat big plans. Clear ownership, metrics, and feedback loops outperform vague ambition. At Amazon, we call these “mechanisms.” The best leaders focus teams on what they can control, even amid uncertainty. 5. Senior leaders as champions and energizers. The best leaders inject speed into organizational processes. They roll up their metaphorical sleeves, ask questions, break silos, remove friction, and energize teams to think bigger and move faster. It’s an art as much as a science. I’m grateful to the teams, leaders, customers, and partners I’ve worked with over the past decade, and excited to keep building as AI and cloud infrastructure continue to evolve. Onward.

126

8 Comments

Some timeless lessons from my recent conversation with Amit Somani on AI, leadership, and product-building 👇 AI is reshaping how we build, lead, and innovate, but the fundamentals of great product-building remain timeless. Our discussion reminded me that while technology accelerates what’s possible, clarity of purpose and customer empathy continue to define success. A few takeaways that stood out for me: Customer obsession still drives the best products ,empathy can’t be automated. Real adoption is the true test of AI ,value must be measurable and tied to business impact. Defensibility now comes from continuous innovation and deep customer insight, not just tech moats. Big orgs win when they nurture startup style teams and room to experiment. Product leaders succeed by balancing vision with execution ,staying close to customers and taking smart risks. 👉 What principles guide your approach to product-building in the AI era? #AI #ProductManagement #Leadership #Innovation #ProductStrategy #Tech

39

3 Comments

"For these models to reach their peak value, you need to train them not just on publicly available data, but make privately owned data available for those models as well," - Ellison https://lnkd.in/gM6FskzJ

4

When to Say No (and When Not To) Great product leadership needs high judgment. The ability to choose the right opportunity at the right time. When I got the scope to build Amazon’s large item delivery experience, I was excited. It felt like a big opportunity to make an impact. My instinct was to say yes to everything, move fast, and get results quickly. Then came my first real challenge. Customers had little visibility into their deliveries. Escalations were piling up. To understand where things were breaking, we needed full tracking data from third-party carriers. When I asked for data on every shipment, they laughed. The best they could offer was a small sample. Taking it would have been easy. It would have allowed quick progress using averages. But it was not enough to meaningfully improve the customer experience. I said no. That decision slowed us down a bit, but sparked a journey of change. We fixed operational gaps, redesigned processes, and improved the delivery experience by 2000 basis points. That same carrier became a stronger, more competitive partner for every client they served. But saying no is not always the right move. Earlier in that project, before carriers could send automated feeds, they offered manual data files. A teammate wanted to reject it because of the errors and time it would take. I convinced them to say yes. I worked with data engineering to load the files into a database and wrote SQL queries to finally understand the state of the business. It was not perfect, but it gave us the insight to start solving real problems. Product leadership needs high judgment. Knowing when to push back to protect focus and create meaningful change, and when imperfect steps will help you learn and build momentum. Both matter if you want to create a lasting impact.

14

5 Comments