Exploring the Challenges of AI Conversations and User Experience

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 communicate with AI. 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.

All episodes of the podcast are also available on Spotify, Apple and YouTube.

New to the pod? Subscribe below to get the next episode in your inbox 👇

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!

If you’d like to watch the video of our conversation, you can catch that on YouTube:

Links:

* Kavita Anand: https://www.linkedin.com/in/kavitaanand05/

* Willow Voice (Get the first month free by using this link!): https://willowvoice.com/?ref=BEREZ64

* Marc: https://www.linkedin.com/in/marcbaselga/

* Ben: https://www.linkedin.com/in/benerez/

To support the podcast, please check out the links below:

* Supra has teamed up with Maven to bring you something special – courses that our own community members have personally curated. And because you're part of the Supra family, you get $100 off any of these handpicked selections with code SUPRAxMAVEN.

* Preparing for a PM interview with tech companies like Meta and Google? Check out Ben's course for Product Sense and Analytical Thinking PM interviews (selected by Lenny Rachitsky as a Top Course in Product on Maven 🔥) and his AI Copilot for interview practice. Supra Insider listeners get 10% off the course with promo code “suprainsider”. Enrollment is now open for the next cohort starting July 15th.

If you enjoyed this conversation, please share it with a friend or colleague 👇

Also, if you’re a new subscriber, we encourage you to check out some of the recent episodes you might have missed:

And here are some less recent favorites:

This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit suprainsider.substack.com