Claude Mobile App Improvements

Improvements to drive more usage in Claude Mobile app

<aside> <img src="https://s3-us-west-2.amazonaws.com/secure.notion-static.com/22fe7f25-b6f4-4e52-a825-2fd468726acf/Ellipse_37.png" alt="https://s3-us-west-2.amazonaws.com/secure.notion-static.com/22fe7f25-b6f4-4e52-a825-2fd468726acf/Ellipse_37.png" width="40px" /> Claude Mobile App Improvements PRD

</aside>

Winning in AI coding agents space

Winning in AI coding agents space

<aside> <img src="https://s3-us-west-2.amazonaws.com/secure.notion-static.com/22fe7f25-b6f4-4e52-a825-2fd468726acf/Ellipse_37.png" alt="https://s3-us-west-2.amazonaws.com/secure.notion-static.com/22fe7f25-b6f4-4e52-a825-2fd468726acf/Ellipse_37.png" width="40px" /> Winning in AI coding agents space

</aside>

Evals for your AI Product : A Product Manager's Guide

Mental model around what are LLM agents and how do they different standalone LLM applications.

<aside> <img src="https://s3-us-west-2.amazonaws.com/secure.notion-static.com/22fe7f25-b6f4-4e52-a825-2fd468726acf/Ellipse_37.png" alt="https://s3-us-west-2.amazonaws.com/secure.notion-static.com/22fe7f25-b6f4-4e52-a825-2fd468726acf/Ellipse_37.png" width="40px" /> Evals for your AI Product

</aside>

Demistifying LLM Agents

Mental model around what are LLM agents and how do they different standalone LLM applications.

<aside> <img src="https://s3-us-west-2.amazonaws.com/secure.notion-static.com/22fe7f25-b6f4-4e52-a825-2fd468726acf/Ellipse_37.png" alt="https://s3-us-west-2.amazonaws.com/secure.notion-static.com/22fe7f25-b6f4-4e52-a825-2fd468726acf/Ellipse_37.png" width="40px" /> Defining LLM Agents

</aside>

Evaluating LLM powered products

Framework to define the task LLM needs to solve, evaluation criteria, and evaluation dataset.

<aside> <img src="https://s3-us-west-2.amazonaws.com/secure.notion-static.com/22fe7f25-b6f4-4e52-a825-2fd468726acf/Ellipse_37.png" alt="https://s3-us-west-2.amazonaws.com/secure.notion-static.com/22fe7f25-b6f4-4e52-a825-2fd468726acf/Ellipse_37.png" width="40px" /> Measuring efficacy of LLM powered products

</aside>

AI layers, leverage and risks