Product Launch

DoorDash Launches Command Line Tool for AI Agents

DoorDash has introduced a limited beta of DoorDash CLI, a command-line tool that lets developers order food directly from their AI agents. The tool, called dd-cli, allows users to search stores, find deals, and check out. It is currently open to U.S. and Canadian macOS developers via a waitlist.

Neura News

Neura News

Neura Market Editorial

July 16, 20263 min read
DoorDash Launches Command Line Tool for AI Agents

DoorDash has launched a limited beta of a command-line interface tool that lets developers order food directly from their AI agents. The tool, called DoorDash CLI or dd-cli, allows users to search stores, find deals, and complete purchases, according to the company.

A New Tool for Developers

The company announced the beta on July 15, 2026, via a post on X by DoorDash co-founder and CTO Andy Fang. The post included a video demonstrating the tool in action. The new CLI is open to U.S. and Canadian macOS developers who join a waitlist. DoorDash was asked for comment about the new feature.

The announcement has drawn attention partly because of its humorous nature. Command-line tools are typically associated with programming tasks, not ordering lunch. The idea of an AI agent running commands to order a salad or sandwich can seem absurd at first glance.

Agentic Commerce in Practice

Despite the humor, the DoorDash CLI is not a joke. It represents a real example of what the company calls agentic commerce. By exposing DoorDash's ordering platform to AI agents, the company allows developers to integrate food ordering capabilities into their own software and services.

Instead of using the DoorDash app directly, developers can build custom tools for ordering food, groceries, or finding local lunch deals. These capabilities can also serve as building blocks that combine with other tools.

The #1 Newsletter in AI

Stay ahead of the AI curve

The most important updates, news, and content — delivered weekly.

No spam. Unsubscribe anytime.

DoorDash has already experimented with offering its service through iMessage and has its own AI chatbot called Ask DoorDash. The company also exposes its service to AI chatbots like OpenAI's ChatGPT and Claude.

Building on the Concept

The sign-up form for the CLI beta includes a field asking developers what they would build if granted access. This suggests DoorDash is interested in seeing creative applications of the tool.

The launch also carries a touch of programming humor. It recalls an old XKCD comic where a programmer says "make me a sandwich" and another person responds "What? Make it yourself." The programmer then says "sudo make me a sandwich" and the other person complies. The video attached to the X post leans into this over-engineering theme.

In the video, the tool reads Slack messages, recalls memories, parses JSON, inspects menu structures, runs Python scripts, recovers from errors, and calculates totals, all to accomplish something as simple as ordering three salads. As the task runs, the interface displays the word "Flibbertigibbeting," adding to the humor.

Related on Neura Market

More from Neura News

AI Models

42 Mathematicians Urge Royal Society to Warn Government and Media About AI Existential Risk

Forty-two mathematical fellows, including Fields Medal winners Martin Hairer, Peter Scholze, and Wendelin Werner, have signed an open letter urging the Royal Society to warn the UK government and media about existential risks from advanced AI. The letter follows recent breakthroughs in which leading models solved open research problems, including a Millennium Problem. None of the signatories are affiliated with AI companies. The group warns that AI labs' estimates of existential risk above ten percent must not be dismissed as hype, and that by the time the situation becomes obvious to the public, it may be too late to act.

Sep 18·2 min read
Developer

Steve Yegge Shuts Down Gas Town After Failing to Build Anything Else With It

Steve Yegge shut down Gas Town, his ultra-vibed coding agent orchestrator, after admitting he never built anything else with it despite heavy subscription spend. Databricks reported a 60% coding spend increase after rolling out GPT-6 Astra to 3,500 engineers, OpenAI published a misalignment disclosure framework with six case reports, and Xiaomi ran MiMo-V2.6 RL training in public with live telemetry.

Sep 18·21 min read