What happened
DoorDash introduced DoorDash CLI (dd-cli), a command-line tool that lets developers order food through their AI agents. The tool can search stores, find deals, and complete checkout. Access is available in limited beta to U.S. and Canadian macOS developers via waitlist, announced by DoorDash co-founder and CTO Andy Fang on July 15, 2026.
Why it matters
The move exposes DoorDash's ordering platform directly to AI agents and developer tools, letting builders integrate food ordering into their own software and services rather than requiring users to leave and visit DoorDash's app. This is an example of what agentic commerce—where AI agents handle transactions on a user's behalf—can look like in practice.
What to watch
DoorDash's signup form for beta access asks developers what they would build with the tool, suggesting the company is actively exploring what use cases developers see for agent-driven ordering. The company already offers ordering via iMessage and operates its own chatbot called Ask DoorDash, as well as exposing its service to third-party AI chatbots like OpenAI's ChatGPT and Claude.
Summaries like this, in your inbox every morning.
DoorDash's CLI launch reflects a broader shift toward agentic commerce, where AI agents execute transactions on a user's behalf. While the announcement has generated attention partly because of its humorous angle—automating something as mundane as ordering lunch via command-line recall the XKCD programmer joke about "sudo make me a sandwich"—the underlying strategy is serious: the company is opening its ordering platform to third-party developers and AI systems, not just users. This approach allows developers to embed DoorDash functionality into their own tools and services, turning food ordering into a building block that can be combined with other capabilities. DoorDash has already experimented with alternative ordering channels, including iMessage and its Ask DoorDash chatbot, and integrations with OpenAI's ChatGPT and Claude. The CLI is an extension of that same principle—exposing the service's infrastructure to agents and tools outside of DoorDash's direct control. By asking beta participants what they would build, the company signals it is genuinely exploring the boundaries of agentic commerce rather than simply offering a novelty feature.
Pick your industry and the AI tools you use, and get news related to your work every day.
Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.
Reflection AI introduced Beam, an open-weight model for agentic coding and long-horizon tasks, with 501 billio…
The walkthrough points the CLI at a local mock via the ANTHROPIC_BASE_URL environment variable
A developer released agent-guardrails, a one-script Python standard-library plugin that guards Bash, Write, Ed…
A Zenn guide explains systems to install before letting AI agents, bots or scheduled jobs post, send, publish…
A non-engineer operator says one person ships four smartphone apps on Google Play, three on the App Store, wit…
Researchers at Microsoft published a paper titled "Adoption and Impact of Command-Line AI Coding Agents: A Stu…
