Windows Errors? Fix Them Before They Spread
Repair common Windows errors and clear accumulated junk for a smoother, more stable PC - no reinstall needed.Free scan · no reinstallCrashes, No Sound, or Screen Glitches?
Random freezes, missing sound and display glitches usually trace back to one bad driver. Find and replace yours safely.Free scan · under a minuteBrian Chesky’s argument is that useful AI agents need a platform layer—with shared capabilities and developer interfaces—so they can work across apps and services. That is a proposal, not a universal agent operating system Airbnb has shipped. He also argues that travel discovery calls for more than a chat box: people need ways to browse, compare and plan together.
What does Chesky mean by an AI operating system?
In an October 1, 2026 interview with TechCrunch’s Ivan Mehta, Airbnb co-founder and CEO Brian Chesky said current AI applications still run on familiar platforms such as iOS, macOS and Windows, which he does not consider operating systems built for AI. His envisioned layer would put agent capabilities lower in the software stack, where agents and other components could interact. He also says a platform needs a software-development kit (SDK) that exposes what applications can do.
This is not a claim that Airbnb is launching a phone or desktop operating system. Chesky is describing enabling infrastructure: a way for agents to access app capabilities and coordinate across services, rather than relying only on isolated chatbots or company-to-company integrations. He characterizes the current race as a contest to become the primary agent—the “quarterback”—but says a leading agent alone would not provide the broader interfaces and interoperability he wants. TechCrunch’s interview is the source for his views and product plans.
Why does he think chatbots are a poor fit for travel discovery?
Chesky argues that chat interfaces can make browsing and shopping cumbersome: they show only a few choices at a time, and it may take several exchanges to get to a useful result. For a simple task—“Book me a flight, I don’t want to look at it”—that may be exactly what a customer wants. Airbnb travel discovery, in his view, is different: exploring options and anticipating a trip can be part of the experience.
#1 Best Overall
He has said, “I think that I’ve believed for a long time that a chatbot isn’t the right interface for e-commerce.” His point is not that chat has no role, but that chat alone can hide too much choice and make collaborative planning awkward. Group trips may benefit from what he calls “multiplayer” AI, where several people can participate together.
Chat-first and browse-and-compose interfaces
| Design question | Chat-first approach | Browse-and-compose approach |
|---|---|---|
| Seeing options | Typically presents a small set at a time, according to Chesky. | Can keep multiple options visible for browsing and comparison. |
| Interaction | May require several turns to refine a request. | Lets people inspect and adjust choices directly, alongside generated assistance. |
| Group planning | Can be difficult if a single conversation is the only shared surface. | Can support a shared view in which participants compare and discuss choices. |
| Control and platform tasks | May not expose predictable controls for every service-specific action. | Can combine generative screens with designed functions such as maps, host messaging, identity verification and adding other items. |
Chesky expects a mix of designed interface elements and generative screens, rather than either a pure chatbot or a conventional app frozen in its first design. He said, “I think that there’s going to be some interface that is, you know, I don’t want to call it a midpoint, but something between a chatbot and what you see in the first version we shipped.”
How is Airbnb preparing for agents?
Chesky says Airbnb is making its infrastructure more agent-friendly. He imagines specialized agents across parts of Airbnb’s service and, eventually, a broader Airbnb agent that could work with other agents through MCP. He also discusses voice agents. These are stated directions and expectations; the interview does not establish that a universal, cross-service agent experience is already available.
For an agent to do more than answer questions, it needs a way to hand a user into the service’s actual capabilities. In Airbnb’s case, that could mean supporting browsing, comparing stays, messaging hosts, verifying identity, using maps and adding other trip components. Chesky suggests either a handoff or richer developer interfaces could preserve such functions. He sees agents as a possible way to make services more interoperable even where conventional integrations have depended on individual business deals.
Recommended Free Tools
Rank #3
- Incredibly Light. Surprisingly Thin. - LG gram is designed to go wherever you do. Weighing just 2.5 lbs. with an ultra-slim 0.7-inch profile, it slips easily into your bag and feels light in hand—making it effortless to carry, commute, and work from anywhere.
- Remarkably Light. Reliably Strong. - LG gram has passed seven military-grade durability tests, striking an impressive balance between a highly portable, lightweight metal build and the confidence to handle everyday movement and travel.
- Power That Last with Smart Efficiency - LG gram combines a high-capacity 72Wh battery with AI-driven power management to optimize efficiency based on your usage. The result is up to 32 hours of video playback for} long-lasting performance that keeps up with your day—at home, at work, or wherever you go.
- AMD Ryzen AI Performance - Powered by AMD’s AI-optimized Ryzen processor with Radeon Graphics and a built-in NPU, LG gram delivers smooth multitasking and responsive performance. Fast 32GB LPDDR5x memory and 1TB NVMe storage keep everything moving without slowdowns.
- Dual AI for Always-On Intelligence - LG gram’s Dual AI—powered by EXAONE 3.5, LG’s AI solution—combines gram chat On-Device AI and gram chat Cloud AI to deliver seamless assistance. gram chat On-Device AI enables fast document search and summarization directly on your PC, while gram chat Cloud AI expands capabilities when connected—so everyday tasks stay smooth, responsive, and uninterrupted.
Chesky also says that, in his own use, Airbnb works poorly through the consumer agents Muse and Instinct, and he extends that criticism to hotel booking. That is his assessment, not an independent benchmark of those agents. He sums up the broader problem this way: “I don’t think we’ve cracked consumer AI.”
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.What would an agent operating system have to manage?
Two 2026 arXiv preprints offer technical context for the idea, but neither establishes a settled architecture or standard. One paper, “Agent Operating Systems (AOS): Integrating Agentic Control Planes into, and Beyond, Traditional Operating Systems”, describes how long-running agents that pursue goals, use tools and adapt to feedback can strain conventional operating-system boundaries. It outlines potential system responsibilities including:
- Scheduling agent work and coordinating execution.
- Managing context and memory over time.
- Registering tools and capabilities, and controlling access to them.
- Enforcing policy and trust boundaries.
- Making actions observable and auditable.
Those responsibilities point to why “an agent that can call tools” is not the whole platform question. A system also needs to decide which agent can do what, preserve relevant state, and make consequential actions inspectable. The paper frames possible responsibilities; it is not evidence that a single implementation has solved them.
A second preprint, “Towards an Agent Operating System – Lessons from Classical and Cloud OS”, describes agent systems as experimental, with many frameworks and protocols but no community consensus on core abstractions or guarantees. Its authors argue for precise, portable abstractions and standardization. The two papers leave open design choices such as whether agent control sits in a user-space runtime, an operating-system layer or a distributed control plane; how state is managed; how permissions are enforced; and how actions are monitored and audited. They do not identify Chesky’s proposal as the accepted answer.
Best Value
Is an AI-agent operating system already a standard?
No. Chesky is making a platform-layer argument, while the technical literature cited here describes an unsettled field. There is no established universal agent operating system shown in the interview or these preprints, and no evidence that all apps or services can already interoperate through a common interface.
Chesky’s position is that a genuine shift from apps to agents requires platform-level support, not just better chatbots. He says, “It’s really up to Apple or Google, or somebody, to build a new platform for us to really make the true shift from apps to agents.” Whether that layer emerges from established operating-system companies, new infrastructure or a combination remains an open question.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
