intelligent reply to Perplexity cofounder blog post: Bullying is Not Innovation The point of technology is to make life better for people. We call it innovation, but it’s just the constant process of asking how to make things better. Bullying, on the other hand, is when large corporations use legal threats and intimidation to block innovation and make life worse for people. This week, Perplexity received an aggressive legal threat from Amazon, demanding we prohibit Comet users from using their AI assistants on Amazon. This is Amazon’s first legal salvo against an AI company, and it is a threat to all internet users. For the last 50 years, software has been a tool, like a wrench in the hands of the user. But with the rise of agentic AI, software is also becoming labor: an assistant, an employee, an agent. The law is clear that large corporations have no right to stop you from owning wrenches. Today, Amazon announced it does not believe in your right to hire labor, to have an assistant or an employee acting on your behalf. This isn’t a reasonable legal position, it’s a bully tactic to scare disruptive companies like Perplexity out of making life better for people. A Threat to User Choice Amazon wants to block you from using your own AI assistant to shop on their platform. Here's what they're trying to prevent: You ask your Comet Assistant to find and purchase something on Amazon. If you're logged in to Amazon (credentials in Comet are stored securely only in your device, never on Perplexity’s servers), the Comet Assistant quickly finds and purchases the item for you, saving you time for more important tasks. Or, you can ask it to compare options and purchase the best one for your needs. Comet users love this experience. Amazon should love this. Easier shopping means more transactions and happier customers. But Amazon doesn’t care. They’re more interested in serving you ads, sponsored results, and influencing your purchasing decisions with upsells and confusing offers. How do we know? CEO Andy Jassy told investors just last week: "It just all leads to a return on advertising spend that's very unusual,” he bragged (47:50), and in the same call he admitted, “We’re also having conversations with and expect over time to partner with 3rd party agents.” (41:38). Read that again. Amazon wants to eliminate user rights so that it can sell more ads right now and partner with AI agents designed to take advantage of users later. It’s not just bullying, it’s bonkers. Every retailer should celebrate the art and science of merchandising, which is when merchants create delightful customer experiences in the shopping journey. But it’s dangerous to confuse consumer experience with consumer exploitation. Users want AI they can trust, and they want AI Assistants that work on their behalf and no one else’s. The Future of User Agents User agents are exactly that: agents of the user. They're distinct from crawlers, scrapers, or bots. A user agent is your AI assistant—it has exactly the same permissions you have, works only at your specific request, and acts solely on your behalf. Assistive AI is becoming an increasingly important aspect of the global economy, businesses everywhere, and the individual rights and capabilities of every person. We believe it’s crucial to raise awareness about the issues facing user agents. For user agents to serve their true purpose, they must be: 1. Private. Your AI assistant must be indistinguishable from you. When Comet Assistant visits a website, it does so with your credentials, your permissions, and your rights. (It’s also unable to do anything you can’t). Publishers and corporations have no right to discriminate against users based on which AI they've chosen to represent them. Users must have the right to choose technologies that represent them. Privacy and freedom of choice depend on this. 2. Personal. Your user agent works for you, not for Perplexity, and certainly not for Amazon. For decades, machine learning and algorithms have been weapons in the hands of large corporations, deployed to serve ads and manipulate what you see, experience, and purchase. The transformative promise of LLMs is that they put power back in the hands of people. Agentic AI marks a meaningful shift: users can finally regain control of their online experiences. 3. Powerful. Your AI assistant must be capable of any task that matters to you. Users have a right to select high-performing AI agents from the cutting edge of innovation. The technology available to users can’t be hamstrung just because it threatens some public company’s pressure to deliver more ad revenue. The future of AI, like all technology, is for people. Perplexity Will Not Be Intimidated The rise of agentic AI presents a choice. Will this technology empower users to take control of their digital lives? Or will it become another tool for corporations to manipulate and exploit? Perplexity is fighting for the rights of users. People love our products because they’re designed for people. User choice and freedom are at the heart of everything we build. Perhaps that’s what makes us a target for corporate bullies. But Amazon shouldn’t forget what it’s like to be our size and passionate about a world-changing product. They too once faced intimidating threats and fought aggressively in every case to give users a better choice. Amazon also forgets how it got so big. Users love it. They want good products, at a low price, delivered fast. Agentic shopping is the natural evolution of this promise, and people already demand it. Perplexity demands the right to offer it.