#65: How to build an AI career coach in 90 minutes | Kavita Anand (VP, Product & Design @ NewtonX) скачать в хорошем качестве

#65: How to build an AI career coach in 90 minutes | Kavita Anand (VP, Product & Design @ NewtonX)

What if you could access a personalized career coach anytime—one who remembers your goals, understands your tendencies, and gives you thoughtful, actionable guidance? In this episode of Supra Insider, Marc and Ben sit down with Kavita Anand, a product leader at NewtonX, to explore how she built her own AI-based career coach using tools like Claude and ChatGPT—and then taught 30+ women at her company how to do the same. She breaks down the exact system she used: crafting a system prompt, running a kickoff conversation, and curating relevant context to create a truly helpful AI co-pilot. They also explore how to avoid common pitfalls like getting generic advice or triggering confirmation bias, and why voice-based AI interfaces are changing how people reflect and process career challenges. Whether you’re a product leader, an early-career PM, or just AI-curious, this episode will show you how to start designing an AI coach that works the way you want—even if it takes a little tinkering. In this episode, we covered the following topics: (02:38) Kavita shares how she adapted ideas from a Supra-led workshop to run a 90-minute session with 30+ women at NewtonX. (06:01) The three components of an effective Claude-based co-pilot: system prompt, project knowledge, and chat threads. (08:13) How participants personalized their AI coaches to reflect their needs, coaching preferences, and role-specific challenges. (10:10) Kavita’s personal use case: how AI coaching gives her access and emotional freedom that human coaches can’t. (14:29) Why the biggest limitation of AI coaching is often the user, not the model—and how to give better context. (26:40) Prompt engineering tactics that dramatically improve AI outputs—like role prompting, decomposition, and self-critique. (30:00) Building a Claude project from scratch: writing a system prompt and refining it with live feedback. (45:38) Why adding too much unstructured project knowledge can harm output—and how to curate and index it effectively. (49:38) Live demo: AI coach reacts to a real-world workplace challenge with thoughtful, adaptive follow-up questions. (54:23) Designing workshops to ensure participants get to their “aha” moment and leave with a working AI copilot. And more! --- Links: Kavita Anand:   / kavitaanand05   Willow Voice (Get the first month free by using this link!): https://willowvoice.com/?ref=BEREZ64 Marc:   / marcbaselga   Ben:   / benerez   #ai #artificialintelligence #genai #copilot #product #productivity #podcast