Vedant Choubey

Introducing Antigravity 2.0, a new standalone desktop application that delivers fully on that original glimpse of a truly agent-optimized experience. Rebuilt from the ground up with multi-agent teams, scheduled tasks, native voice and one-click integration with other Google products. Learn how to get started with Antigravity 2.0 👇

@shreyas Most PMs don't slow down to think, they slow down to collect more data in an effort to hedge against all gaps. More data feels safer. But information at any point is incomplete. The right call is generally visible from the get go, the skill is to be able to recognise it

The most harmful misconception among product people is believing they have to choose between moving fast and making good product decisions. Good product decisions don’t actually take more time, they take more skill. Like how Magnus Carlsen sees the best chess move in a few seconds, a move we wouldn’t find even if we had a whole week.

@JustAnotherPM An elegant breakdown of the entire picture. In my view traditional metrics show output: Did the numbers move. The AI layer adds outcome metrics that are lagging. Did the model deliver desired value? Answers don't surface immediately due to the entry of a probabilistic layer.

Every Product Manager thinks they can "figure out AI" when they need to. They're wrong. I've been too many product reviews where PMs confidently presented AI features they didn't understand. The results were painful to watch. Here's what traditional PM experience actually teaches you about AI PM (spoiler: not much): 𝗥𝗲𝗾𝘂𝗶𝗿𝗲𝗺𝗲𝗻𝘁𝘀 𝗪𝗿𝗶𝘁𝗶𝗻𝗴 ↳ Traditional: "Sort search results by price" ↳ AI PM: "Rank results based on user preferences and intent using behavioral signals" The shift? From precise instructions to desired outcomes. 𝗧𝗲𝘀𝘁𝗶𝗻𝗴 𝗦𝘁𝗿𝗮𝘁𝗲𝗴𝘆 ↳ Traditional: A/B test → observe → ship winner ↳ AI: Offline evaluation → shadow testing → human review → gradual rollout You're not just testing features—you're validating model behavior and output accuracy. 𝗦𝘂𝗰𝗰𝗲𝘀𝘀 𝗠𝗲𝗮𝘀𝘂𝗿𝗲𝗺𝗲𝗻𝘁 ↳ Traditional: Engagement, conversion, NPS ↳ AI: All of the above PLUS precision, recall, model accuracy You need to speak both languages: business metrics and model performance. 𝗣𝗼𝘀𝘁-𝗟𝗮𝘂𝗻𝗰𝗵 𝗥𝗲𝗮𝗹𝗶𝘁𝘆 ↳ Traditional: Monitor adoption, optimize features ↳ AI: Monitor model drift, manage retraining pipelines, collect feedback data An AI product literally evolves after launch. 𝗧𝗲𝗮𝗺 𝗖𝗼𝗹𝗹𝗮𝗯𝗼𝗿𝗮𝘁𝗶𝗼𝗻 ↳ Traditional: Engineers, designers, analysts ↳ AI: Add ML engineers, data scientists, data engineers, compliance teams The skill that matters most? Translation between business needs and technical constraints. The opportunity is massive. But you need to start learning the new language of data, models, and probabilities—paired with the product mindset you already have.

I have lots of really cool newsletters coming into my personal email. But I rarely ever read them. They arrive on random days and get buried in my inbox and the friction to scroll through my email, find good ones to read and finally open one becomes just too much effort for me sometimes. By the time Sunday arrives, when I have some time to read, I've forgotten they exist. So I thought why not build a basic AI agent that automatically does all the work for me? 🛠️ So here's what I Built! Spent a weekend making the perfect use of my personal Claude Pro. An autonomous AI agent that runs every Saturday at 12:30 PM, reads my favourite newsletter emails from the past 7 days, summarises each one using an LLM, and sends me a single clean digest, straight into my inbox. No manual trigger. Just an email already waiting for me every Saturday afternoon. ⚙️ Here's my technical approach: 1. I integrated Gmail API that reads and fetches all newsletter emails from the past 7 days 2. Each email's content is passed to Groq's API, which generates a crisp summary for me to get the gist of the articles 3. All summaries are compiled into a single well formatted digest email 4. Resend delivers it to my inbox in a cool minimalist template that I designed using Claude Design 5. The entire flow is triggered automatically every Sunday via a Vercel Cron Job, zero manual intervention 🧱 Tech Stack: - Next.js 15 + TypeScript: The application framework that ties everything together - Gmail API + OAuth 2.0: Securely connects to my inbox and reads emails on my behalf - Groq API: The AI brain that summarises each newsletter into key takeaways - Resend: Sends the final digest email to my inbox - Vercel + Cron Job: Hosts the agent and triggers it automatically every Saturday at 12:30 PM - Claude Code: AI coding agent used to build and ship the entire project - Claude Design: Designed the email digest UI and handed it off to Claude Code for integration The best part? The problem definition took 5 minutes. The build took just a few hours 😃 #ProductThinking #AgenticAI #ClaudeCode #ClaudeDesign #Automation