How to Build ChatGPT Apps (The Next App Store?) | Live Demo by Colin Matthews

Jan 22, 2026

Colin Matthews, an AI product builder and prototyping expert, joins to discuss the future of ChatGPT apps. He explains how these apps could revolutionize user interaction by embedding branded solutions directly into chats. Colin highlights the benefits of integrated distribution compared to traditional app stores and explores various consumer use cases, from to-do lists to healthcare tools. He also emphasizes the importance of app testing, metadata optimization, and team structure for success in this emerging landscape.

Ask episode

AI Snips

Chapters

Transcript

Episode notes

INSIGHT

Embedded Apps Change Distribution

ChatGPT apps embed branded, interactive experiences directly into conversations so users can interact with applications without leaving chat.
This shifts discoverability and distribution power toward the chat platform's marketplace and UI widgets.

ADVICE

Use Apps To Control Brand Experiences

Build an app to control how your brand appears inside ChatGPT rather than relying on web search extraction.
Focus on deterministic experiences like carts or branded flows that drive higher-intent conversions.

INSIGHT

MCP Is The Universal Tool Protocol

MCP (Model Context Protocol) is the underlying open standard that lets chat AIs call external tools and power app integrations.
Widgets on top of MCP let platforms render interactive UIs returned by tools inside chat.

Get the Snipd Podcast app to discover more snips from this episode

Get the app

This is a free preview of a paid episode. To hear more, visit www.news.aakashg.com

Today’s Episode

ChatGPT Apps might be the next billion-dollar opportunity.

Or they might be another ChatGPT feature that gets abandoned in 6 months.

I genuinely don’t know yet.

But when people say “this could be the new App Store,” my ears perk up. I spent four years building an iOS app in the early days of the App Store. The distribution was incredible. We grew fast purely because of where we were.

So when OpenAI announced the ChatGPT App Store, I needed to understand it.

I brought in Colin Matthews to break it down. Colin is one of my go-to sources for technical product topics. Our AI prototyping collaborations have been some of your favorite episodes.

Today, we’re exploring ChatGPT Apps and what they mean for you as a product builder.

----

Check out the conversation on Apple, Spotify and YouTube.

Brought to you by:

* Maven: Get $500 off with my code on Coil Build ChatGPT Apps course

* Vanta: Automate compliance, Get $1,000 with my link

* Land PM job: 12-week experience to master getting a PM job

* Mobbin: Discover real-world design inspiration

* NayaOne: Airgapped cloud-agnostic sandbox

----

If you want access to my AI tool stack - Dovetail, Arize, Linear, Descript, Reforge Build, DeepSky, Relay.app, Magic Patterns, and Mobbin - for free, grab Aakash’s bundle.

Are you searching for a PM job? Join me + 29 others for an intensive 12-week experience to master getting a PM job. Only 23 seats left.

----

Key Takeaways:

1. ChatGPT apps = MCP + widgets - The Model Context Protocol (invented by Anthropic) lets AI agents call external tools. OpenAI added UI widgets on top to create embedded app experiences directly in chat.

2. 900M weekly active users = massive distribution opportunity - This is the new SEO. Early data shows 26% higher conversion from AI traffic vs traditional search. Every enterprise will eventually build here.

3. You're building for multiple platforms - MCP works across ChatGPT, Claude (coming soon), Cursor, and other AI tools. Build once, distribute everywhere. Gemini doesn't support it yet.

4. Apps get called based on tool descriptions - Your metadata matters. Like SEO but for LLMs. Run evals to test if correct prompts trigger your tools. Iterate on descriptions to improve discovery.

5. Three eval categories: direct, indirect, negative - Direct: user names your app. Indirect: user describes outcome. Negative: irrelevant request shouldn't trigger your tool. Test all three systematically.

6. PMs should prototype but engineers ship production - Use tools like Chippy to prototype quickly and test concepts. Show stakeholders real interactions. Engineering team builds the production version.

7. Enterprise-first, solo builders second - Large companies (Target, Uber, Canva) are early adopters chasing distribution. But huge opportunity for indie builders once public marketplace launches.

8. Best opportunities: embedded collaboration tools - Spreadsheets, task lists, whiteboards where ChatGPT can partner with you. Not just search results—actual interactive experiences.

9. Error analysis on observability logs is critical - Track what prompts triggered which tools with what parameters. Look for mismatches between expected and actual behavior. Iterate tool descriptions.

10. Marketplace launching by end of 2024/early 2025 - Currently only launch partners can publish. Public marketplace coming soon means anyone can ship apps and reach ChatGPT's massive user base.

----

Where to Find Colin

* LinkedIn

* Newsletter