DoorDash Brings Office Ordering to the AI Tools Teams Already Use

DoorDash plans to use participating teams' feedback to improve the experience before expanding connector access further.

See more from StockTitan in Google Search and AI answers. Adds StockTitan as a preferred source · opens Google

Add on Google Not now

A new connector lets companies build internal AI tools for team lunches and office restocking, with a broader beta waitlist opening September 30

SAN FRANCISCO--(BUSINESS WIRE)-- An office lunch can start with a message in Slack and turn into a string of follow-ups: choosing a restaurant, collecting everyone's order, and checking when the food will arrive. We want to make it easier for the person putting that meal together.

Today, we're introducing a DoorDash connector for corporate ordering. Companies can connect DoorDash to compatible internal AI tools their teams already use, or to agents they build themselves, so employees can arrange deliveries as part of their workday. SpaceXAI, Vercel, Cognition, Tempo, and Mercor are among our early beta partners using the connector for employee ordering.

The connector gives those agents the ability to find items on DoorDash, build a cart, place an order, and track its arrival. An employee can ask an agent to find a new lunch based on previous orders or set up a recurring daily meal delivery using an eligible corporate meal benefit. Local businesses fulfill the orders, with delivery through DoorDash.

Companies can also build shared tools around the way their teams work. A Slack bot, for example, could collect daily lunch requests in a thread and place the order for the group. Colleagues could add what they want in the conversation, with the bot handling the steps to get it delivered.

For teams keeping an office stocked, a company could connect an agent to its own inventory information and have it reorder snacks, drinks, or supplies through DoorDash as they run low. The company provides the context and instructions, and the connector gives its agent a way to act on them through DoorDash.

For local businesses, these connections offer another way for customers to find and order from them. A team can discover a restaurant for its next lunch through a workplace tool, with the order still running through DoorDash.

The connector uses the Model Context Protocol, or MCP, an open standard for connecting AI applications to external services. Companies can use it with compatible agents, including ones they develop in-house. Access begins at the company level, and employees sign in to their own DoorDash accounts and agree to the terms before connecting an agent to act on their behalf.

We're starting with a limited beta focused on companies ordering for their own employees. We'll use feedback from participating teams to improve the experience before expanding access further.

Beginning September 30, companies can join the waitlist https://developer.doordash.com/en-US/mcp/. We're also expanding beta access to the DoorDash command-line interface, or CLI, for individual developers building agents for personal use.

View source version on businesswire.com: https://www.businesswire.com/news/home/20260930349991/en/

press@doordash.com

Source: DoorDash

Key Terms

model context protocol technical

A model context protocol is a set of rules or guidelines that determine how a financial model interprets and applies information within a specific situation. It helps ensure consistent and accurate analysis by clarifying what data or assumptions are relevant in a given scenario. For investors, it provides clarity on how predictions or assessments are made, increasing confidence in decision-making.

command-line interface technical

A command-line interface is a text-based way to control software by typing short instructions instead of using menus or buttons, like giving written directions to a calculator or remote helper. For investors, it matters because it enables faster, repeatable and automatable access to data and trading tools, reduces manual errors, and creates clear records of actions—helpful for speed, cost control and auditing in technical workflows.