Starbucks runs on a graph. Now agents want in.

Starbucks architect: agents are just another client on your graph | Sharon Gorla

Since 2016, a lot of what happens between tapping the Starbucks app and grabbing your drink has run through a graph API. Then leadership changed, priorities changed, and parts of the platform went back to a monolith. What survived wasn't the implementation. It was the contract.

In this episode I talk with Sharon Gorla, Lead Engineer and Architect at Starbucks. Sharon helped architect a 90-day greenfield proof of concept to prove the point of sale could run on the same platform as mobile and in-store experiences, piloted in 11 stores. We talk through what happened when the org moved under it, why she jokes that GraphQL was accidentally built for AI, and what a decade of platform work taught her about people.

*In our conversation, we get into:*
1. Why AI agents are a new kind of consumer, and what they need from your platform
2. Whether GraphQL had already had its moment before agents arrived
3. Why orders are still orders, whatever the next client is
4. How a kiosk team built on her graph without meetings or a roadmap
5. What survives when leadership, priorities, and tech stacks all change
6. Why you don't need a new platform for AI, and where MCP fits
7. Tokens, context, and the bill that's now coming due
8. Why every technical champion needs an organizational one

Watch to the end for her advice to every architect listening: find your leader champion.

Sharon Gorla, Lead Engineer and Architect, Starbucks.

*Where to find Sharon Gorla:*
- LinkedIn: https://www.linkedin.com/in/sgorla/

*Where to find Dan Boerner:*
- LinkedIn: https://www.linkedin.com/in/dboerner/
- Email the show: onthegraph@apollographql.com

*Related:*
- Apollo GraphQL: https://www.apollographql.com

*In this episode, we cover:*
0:00 The contract survived
0:26 Introduction
2:10 Agents are a new kind of consumer
5:00 Did GraphQL already have its moment?
6:14 Accidentally built for AI?
9:34 Clients come and go
10:36 Making the case inside Starbucks
13:44 A kiosk team that needed no meetings
14:36 Leadership changed. The contract didn't.
18:20 Do agents need a new platform? Where MCP fits
19:51 Tokens, and the bill coming due
21:59 Champion people, not just technology

If you're working to power your AI efforts and APIs are in the way, email me and I'll connect you with other API champions like Sharon — onthegraph@apollographql.com
Subscribe for new episodes. Receive SMS online on sms24.me

TubeReader video aggregator is a website that collects and organizes online videos from the YouTube source. Video aggregation is done for different purposes, and TubeReader take different approaches to achieve their purpose.

Our try to collect videos of high quality or interest for visitors to view; the collection may be made by editors or may be based on community votes.

Another method is to base the collection on those videos most viewed, either at the aggregator site or at various popular video hosting sites.

TubeReader site exists to allow users to collect their own sets of videos, for personal use as well as for browsing and viewing by others; TubeReader can develop online communities around video sharing.

Our site allow users to create a personalized video playlist, for personal use as well as for browsing and viewing by others.

@YouTubeReaderBot allows you to subscribe to Youtube channels.

By using @YouTubeReaderBot Bot you agree with YouTube Terms of Service.

Use the @YouTubeReaderBot telegram bot to be the first to be notified when new videos are released on your favorite channels.

Look for new videos or channels and share them with your friends.

You can start using our bot from this video, subscribe now to Starbucks runs on a graph. Now agents want in.

What is YouTube?

YouTube is a free video sharing website that makes it easy to watch online videos. You can even create and upload your own videos to share with others. Originally created in 2005, YouTube is now one of the most popular sites on the Web, with visitors watching around 6 billion hours of video every month.