DoorDash AI Agent Lets You Text to Order Food
DoorDash announced on Wednesday that it is launching a text-to-order DoorDash AI agent that lets users place orders through Apple Messages. The new tool allows users to send prompts like “order my usual,” and the agent understands that they mean their Friday night order.
The launch marks a shift toward conversational ordering, where a short message replaces the usual routine of opening an app, browsing restaurants, and building a cart by hand. DoorDash says users can also ask for a specific dish and request a local recommendation, making the agent flexible enough for both routine and spontaneous orders.
How the DoorDash AI Agent Works
The DoorDash AI agent runs inside Apple Messages, so there is nothing new to download or install. Users send a plain-language prompt, and the agent interprets the intent behind it.
For example, a message like “order my usual” is recognized as a recurring order rather than a generic request. From there, the agent searches local spots and suggests a cart based on the prompt.
The agent can even text photos of the food it recommends, adding a visual layer to the conversation. That photo feature matters because it lets users confirm a suggestion without leaving the text thread.
What You Can Ask For
According to DoorDash, the agent handles a range of requests. Users can:
Send a vague prompt like “order my usual” and have it matched to a past order
Ask for a specific dish by name
Request a local recommendation when they are unsure what to eat
Build a cart based on whatever prompt they send
The emphasis is on natural language. Instead of filtering by cuisine, price, or distance, users describe what they want and let the agent do the narrowing.
Group Orders With Mixed Preferences
Ordering for a group is one of the more practical use cases DoorDash highlights. The company says the agent can handle mixed dietary preferences and different quantities in one order.
That solves a common friction point. Group orders usually involve passing a phone around, collecting requests, and manually adjusting quantities. If the agent can absorb those variables in a single thread, it could cut down on the back-and-forth that slows group ordering down.
Why DoorDash Is Betting on AI Agents
By launching an AI agent for food ordering, DoorDash is looking to gain an edge over rivals Uber Eats and Grubhub. The move also comes amid a growing push to adopt personal AI agents that can handle tasks without requiring users to navigate apps or websites themselves.
That industry shift is the broader context here. AI agents are increasingly framed as tools that complete tasks on a user’s behalf, not just answer questions. Food ordering fits that model well because the steps are repetitive and the preferences are personal.
For DoorDash, the bet is that convenience wins. If texting an order is faster than tapping through an app, the agent could become the default way frequent users place orders.
Waitlist and Availability
DoorDash is opening up a waitlist for users in the U.S. to try out the new feature. There is no confirmed public rollout date beyond the waitlist opening.
That means access is limited for now. Interested users in the U.S. will need to join the waitlist to be considered for early access, and DoorDash has not shared how quickly spots will be handed out.
Drone Delivery Testing in Northern California
In addition to the new AI agent, DoorDash announced that it will begin testing its delivery drones with select restaurants in Northern California.
The drone testing runs alongside the AI ordering push rather than replacing it. One focuses on how orders are placed, the other on how they are delivered. Together they point to a broader experiment in shortening every step between craving and doorstep.
DoorDash has not shared which restaurants will take part in the drone tests, nor how long the testing phase will run.
What This Means for Everyday Users
For regular users, the appeal is simple: less time spent ordering. A single text could replace several minutes of scrolling, comparing, and building a cart.
The open question is reliability. Vague prompts like “order my usual” depend on the agent correctly reading past behavior and current context. If it guesses wrong, the convenience disappears. How well the DoorDash AI agent handles those ambiguous requests will likely decide how widely the feature gets adopted.
DoorDash has not shared pricing details for the agent, nor a full list of participating restaurants for either the AI feature or the drone tests.
The DoorDash AI agent pushes food ordering toward conversational commerce, where a text thread does the work of an app. With a U.S. waitlist now open and drone testing planned for Northern California, DoorDash is positioning itself at the intersection of AI assistants and delivery logistics.
