Department of Product

Department of Product

Share this post

Department of Product
Department of Product
AI Agents in Practice

AI Agents in Practice

Internal AI Agent use cases and new products from Uber, McKinsey, Figma, Manus, Ramp and more. Get up to speed with how AI agents are used in the real world.

Rich Holmes
Aug 11, 2025
∙ Paid
29

Share this post

Department of Product
Department of Product
AI Agents in Practice
3
Share

🔒DoP Deep goes deeper into the concepts and ideas that are covered in the Weekly Briefing to help you learn lessons from top tech companies. If you’d like to upgrade to receive these in-depth pieces of analysis you can upgrade below. New reports added every month.


“This is the most impactful change we've seen since the dawn of the internet”.

That’s how an Amazon exec described the introduction of AI agents during the launch of the company’s new Bedrock agentic framework.

The hype machine for AI agents is still in overdrive but what is actually happening in the real world?

In this DoP Deep Dive, we’ll try to answer that question together.

It’s been four months since we last took a look at AI Agents in practice and since then we’ve had new dedicated agent products from OpenAI, frameworks for product teams who want to build their own AI Agents and the launch of AI browsers that will perform agentic actions on your behalf.

Keeping on top of all of this is pretty difficult, but this Deep dive is designed to be your ultimate guide to getting up to speed with where we’re at in the real world quickly. We’ll take a closer look at how AI agents are being used internally at companies like Uber and McKinsey, new AI Agent capabilities, as well as new AI Agent features and products.

Coming up:

  • 20+ real-world examples of AI agents in action, including internal use cases from Uber, McKinsey, Figma, Walmart and more

  • How one company created over 8,000 different AI agents for internal use

  • The exact process and framework a leading tech company uses for identifying AI agent opportunities that you can use in your own company

  • Why one company had to pause their AI Agent rollout after creating so many that employees couldn't keep track (and how they fixed this)

  • The latest AI Agent features and capabilities to get up to speed quickly

  • All of the AI agent examples featured in full


Department of Product: Deep

How this new deep dive is structured

There are over 20 different examples of AI Agents in practice in this deep dive. Here’s a preview of some of the examples included:

Upgrade to unlock all use cases

The examples are categorized into 3 core categories:

  1. Internal use cases - companies using AI agents internally. These are often the most difficult types of examples to get hold of but they’re super helpful if you’re interested in AI agents and how they might help at work. We’ll take a look at examples of AI Agents in action from McKinsey, Uber, Walmart and others together.

  2. AI Agent product and features - as well as internal use cases, we’ll take a look at some new AI Agent products and features that have recently been released. We’ll explore what these new AI agent products can do and how you might be able to use them in your own workflows.

  3. Frameworks - new agentic frameworks that product teams can use to build their own AI Agents. This includes AWS’ new agentic framework and others.

Internal use cases - how companies are using AI agents internally

First up, let’s start with internal use cases to understand how companies are using AI agents internally.

This post is for paid subscribers

Already a paid subscriber? Sign in
© 2025 Department of Product
Privacy ∙ Terms ∙ Collection notice
Start writingGet the app
Substack is the home for great culture

Share