Book restaurant tables via OpenTable and Resy
For about a year, the standard demo of an "AI agent" booking dinner ended the same way: the model found the restaurant, showed you the times, and then politely gave up. Task: For about a year, the standard demo of an "AI agent" booking dinner ended the same way: the model found the restaurant, showed you the times, and then politely gave up. In a hands-on test published April 29, 2026, PCWorld watched Claude surface a live Resy availability grid for The Smith and then say, verbatim, "I'm not able to complete the booking on your behalf." ChatGPT's agent mode fared no better — five minutes of slow clicking through OpenTable's web UI, a party-size dropdown it got wrong ("It seems I may have mistakenly selected '2 people' instead of '3 people'"), and a final handoff: "Please take over to enter those details." On August 10, 2026, that gap closed. Yelp announced that ChatGPT users can now access Yelp Reservations and Waitlist to book a table or join a queue at thousands of restaurants across the US and Canada without leaving the chat. Resy, owned by American Express, launched Resy Reservations in ChatGPT for US restaurants the same week. OpenTable powers recommendations globally. This is not a better restaurant finder. It is the first mass-market instance of an assistant completing a real-world transaction inside the conversation — and it is the concrete thing the agentic commerce stack has been building toward while everyone argued about why AI agents haven't gone mainstream. TL;DR — what people are asking How does booking inside ChatGPT actually work? Start with what is publicly confirmed and what is inference, because a lot of coverage blurs the two. Confirmed. Yelp's announcement (authored by Chad Richard, SVP of Business and Corporate Development) describes an expansion of a content partnership struck a few weeks earlier in late July 2026, which had already brought Yelp reviews, ratings, photos, and business attributes into ChatGPT answers. The new layer adds a booking form rendered in the chat. Resy's version surfaces real-time reservation availability directly beneath each venue in the recommendation list, with in-conversation refinement by time, party size, cuisine, or price. Not confirmed. None of the three partners published a protocol name, an endpoint spec, or a schema. What the shape tells you. An interactive card that renders inside the conversation, holds its own state across turns, refreshes live inventory, and submits a form is not something a plain text tool-call produces. It is exactly the shape of OpenAI's Apps SDK, which is built on the Model Context Protocol. In that architecture, a partner runs an MCP server that declares tools — think search_availability(location, party_size, window) and create_reservation(venue_id, slot_id, guest) — alongside an optional web UI rendered in a sandboxed iframe, in one of three display modes (inline, picture-in-picture, fullscreen). The Apps SDK launched with Booking.com, Canva, Coursera, Expedia, Figma, Spotify, and Zillow as pilot partners; a restaurant reservation platform is the most natural possible fifth verb for that surface. The tell that this is not a private one-off is the parallel deployment. American Express also connected Resy to Claude, where diners browse live tables and reserve inside the conversation — and Anthropic's own connector ecosystem is MCP end to end (see our Claude connectors and MCP servers guide). One reservation platform shipping the same capability into two different assistants in the same window is what a protocol looks like from the outside. A bespoke integration does not replicate that cheaply. It is the same convergence we tracked when agent plugins standardized across OpenAI, AWS, Cursor, GitHub, and VS Code. Three layers, and which one broke The third row is the whole story. Everything else was already there. Catch up on AI Curated AI updates on agents, skills, and MCP — delivered to your inbox. Unsubscribe anytime. Recommend vs. transact: why this is a bigger jump than it looks A recommender is allowed to be wrong. If ChatGPT suggests a mediocre Thai place, you shrug and pick another. The cost of a bad output is one wasted paragraph. A transactor is not allowed to be wrong in the same way, because its output has side effects in someone else's system. A hallucinated recommendation is annoying; a hallucinated reservation consumes a real table at a real restaurant on a real Friday night, and someone eats the loss. Crossing that line changes four things simultaneously:; tools: ChatGPT Agent, Claude. Human role: The original post does not say how a person stayed involved.; limitations: Prerequisites: The restaurant must be live on a supported platform (Yelp Guest Manager, Resy, or OpenTable) with accurate structured data. Constraints: Cancellation and modification policies are enforced by the platform, not the AI. Integration uncertainty: The underlying protocol is inferred to be MCP/Apps SDK but not officially confirmed by all partners. Human approval: Users must explicitly confirm booking details in the UI before the transaction is committed..
Tools
Published on Agent Work Atlas:
Overview
For about a year, the standard demo of an "AI agent" booking dinner ended the same way: the model found the restaurant, showed you the times, and then politely gave up.
Workflow
For about a year, the standard demo of an "AI agent" booking dinner ended the same way: the model found the restaurant, showed you the times, and then politely gave up. In a hands-on test published April 29, 2026, PCWorld watched Claude surface a live Resy availability grid for The Smith and then say, verbatim, "I'm not able to complete the booking on your behalf." ChatGPT's agent mode fared no better — five minutes of slow clicking through OpenTable's web UI, a party-size dropdown it got wrong ("It seems I may have mistakenly selected '2 people' instead of '3 people'"), and a final handoff: "Please take over to enter those details." On August 10, 2026, that gap closed. Yelp announced that ChatGPT users can now access Yelp Reservations and Waitlist to book a table or join a queue at thousands of restaurants across the US and Canada without leaving the chat. Resy, owned by American Express, launched Resy Reservations in ChatGPT for US restaurants the same week. OpenTable powers recommendations globally. This is not a better restaurant finder. It is the first mass-market instance of an assistant completing a real-world transaction inside the conversation — and it is the concrete thing the agentic commerce stack has been building toward while everyone argued about why AI agents haven't gone mainstream. TL;DR — what people are asking How does booking inside ChatGPT actually work? Start with what is publicly confirmed and what is inference, because a lot of coverage blurs the two. Confirmed. Yelp's announcement (authored by Chad Richard, SVP of Business and Corporate Development) describes an expansion of a content partnership struck a few weeks earlier in late July 2026, which had already brought Yelp reviews, ratings, photos, and business attributes into ChatGPT answers. The new layer adds a booking form rendered in the chat. Resy's version surfaces real-time reservation availability directly beneath each venue in the recommendation list, with in-conversation refinement by time, party size, cuisine, or price. Not confirmed. None of the three partners published a protocol name, an endpoint spec, or a schema. What the shape tells you. An interactive card that renders inside the conversation, holds its own state across turns, refreshes live inventory, and submits a form is not something a plain text tool-call produces. It is exactly the shape of OpenAI's Apps SDK, which is built on the Model Context Protocol. In that architecture, a partner runs an MCP server that declares tools — think search_availability(location, party_size, window) and create_reservation(venue_id, slot_id, guest) — alongside an optional web UI rendered in a sandboxed iframe, in one of three display modes (inline, picture-in-picture, fullscreen). The Apps SDK launched with Booking.com, Canva, Coursera, Expedia, Figma, Spotify, and Zillow as pilot partners; a restaurant reservation platform is the most natural possible fifth verb for that surface. The tell that this is not a private one-off is the parallel deployment. American Express also connected Resy to Claude, where diners browse live tables and reserve inside the conversation — and Anthropic's own connector ecosystem is MCP end to end (see our Claude connectors and MCP servers guide). One reservation platform shipping the same capability into two different assistants in the same window is what a protocol looks like from the outside. A bespoke integration does not replicate that cheaply. It is the same convergence we tracked when agent plugins standardized across OpenAI, AWS, Cursor, GitHub, and VS Code. Three layers, and which one broke The third row is the whole story. Everything else was already there. Catch up on AI Curated AI updates on agents, skills, and MCP — delivered to your inbox. Unsubscribe anytime. Recommend vs. transact: why this is a bigger jump than it looks A recommender is allowed to be wrong. If ChatGPT suggests a mediocre Thai place, you shrug and pick another. The cost of a bad output is one wasted paragraph. A transactor is not allowed to be wrong in the same way, because its output has side effects in someone else's system. A hallucinated recommendation is annoying; a hallucinated reservation consumes a real table at a real restaurant on a real Friday night, and someone eats the loss. Crossing that line changes four things simultaneously:
Reported result
Actual outcomes: As of August 2026, users can complete bookings and join waitlists directly in ChatGPT for US/Canada venues via Yelp and Resy. However, earlier tests showed agents failing to complete bookings or making errors like selecting the wrong party size. Post-booking management (cancellations, changes) is not handled in-chat; users must return to the reservation platform. No specific success metrics for error rates are published.
Human role
The original post does not say how a person stayed involved.
Limitations
Prerequisites: The restaurant must be live on a supported platform (Yelp Guest Manager, Resy, or OpenTable) with accurate structured data. Constraints: Cancellation and modification policies are enforced by the platform, not the AI. Integration uncertainty: The underlying protocol is inferred to be MCP/Apps SDK but not officially confirmed by all partners. Human approval: Users must explicitly confirm booking details in the UI before the transaction is committed.
Try it
I want to test the in-chat restaurant booking workflow using ChatGPT or Claude. My goal is to book a table for [replaceable: party size] at a [replaceable: cuisine type] restaurant in [replaceable: city/neighborhood] for [replaceable: date and time]. Steps: 1. Ask the assistant to find available restaurants matching my criteria. 2. Review the interactive availability cards provided in the chat. 3. Select a specific time slot and verify the party size and contact details in the form. 4. Stop before final submission and show me the summary of the booking details. 5. Wait for my explicit confirmation before instructing the assistant to submit the reservation. Deliverables: A screenshot or text summary of the booking confirmation code and the manage_url provided by the platform. Quality Check: Ensure the party size matches my request exactly (previous agents often defaulted to 2 instead of 3). If the assistant cannot complete the booking or asks me to leave the chat, report this as a failure. Do not invent a confirmation if the backend does not return one.
Source reports are not independently verified. Publication date is the catalog publication date, not the original article date.