{"slug": "reachy-pizzaiolo-when-a-restaurant-sign-starts-a-conversation", "title": "Reachy PizzAIolo: When a Restaurant Sign Starts a Conversation", "summary": "A developer built Reachy PizzAIolo, an AI-powered conversational restaurant ordering experience using Pollen Robotics' Reachy Mini Lite and Seeed Studio's reTerminal E1003. The system lets customers place and modify orders through natural conversation, with the robot providing physical presence and the display showing visual confirmation. It was tested at a real pizza party, where it successfully took orders from guests.", "body_md": "*Building an AI-powered conversational restaurant ordering experience with Reachy Mini and Seeed Studio's reTerminal E1003.*\n\nWhat if a restaurant sign didn't just display the menu?\n\nWhat if it could **talk to you, understand what you wanted, help you make a choice, update your order as you spoke - and show everything visually at the same time?**\n\nThat is the idea behind **Reachy PizzAIolo**.\n\nIt combines the personality and conversational abilities of [ Reachy Mini Lite](https://www.seeedstudio.com/Reachy-Mini-Lite-Kit-p-6702.html?sensecap_affiliate=bWJooAR&referring_service=link), the physical presence of the\n\n**a sign you can actually have a conversation with.**\n\nI built Reachy PizzAIolo as my entry for Seeed Studio's ** Interactive Signage Contest 2026**.\n\nThis year's contest focuses specifically on **restaurants and dining**, asking makers to rethink what interactive signage could become when combined with technologies such as AI, voice interaction, sensing and IoT.\n\nThat immediately made me wonder:\n\nWhy should the interaction start with the screen at all?\n\nTouchscreens are already everywhere in restaurants. They work well, but increasingly they feel like another computer interface placed between the customer and the restaurant.\n\nA conversation is different.\n\nYou can say:\n\n\"I'd like a Margherita and a Coke.\"\n\nThen:\n\n\"Actually, make that two pizzas.\"\n\nOr:\n\n\"What vegetarian pizzas do you have?\"\n\nOr simply:\n\n\"That's everything.\"\n\nSo rather than building another digital menu, I wanted to see what would happen if **conversation became the primary interface** and the display became its visual companion.\n\nAnd of course, if the robot taking your pizza order happens to look like Reachy Mini, there was only one sensible name:\n\n**Reachy PizzAIolo.** 🤌\n\nThe core interaction is deliberately simple.\n\nA customer speaks naturally to Reachy.\n\nReachy understands the conversation, maintains an order, and communicates changes to the ordering service.\n\nThe E1003 updates to give the customer a persistent visual representation of what has been ordered.\n\nMeanwhile, restaurant staff - whether in the kitchen or front of house - can see the order appear on the active-order dashboard.\n\nThe result is an interaction that combines:\n\n**conversation + physical character + visual confirmation + structured restaurant data**\n\nrather than relying on any one interface alone.\n\nOne of the most enjoyable milestones for the project was getting to use **Reachy PizzAIolo at an actual pizza party**.\n\nRather than only testing the interaction as a controlled demo, Reachy was able to take orders from real guests in exactly the sort of social setting the project was designed for.\n\nIt was a simple but useful test of the idea: people could approach Reachy, place their order conversationally, and see that interaction turn into a structured order.\n\nAnd, perhaps more importantly, it was fun. A robot taking pizza orders naturally became part of the experience rather than just another ordering terminal.\n\n*Reachy PizzAIolo on duty at a real pizza party.*\n\nAt the front of the experience is the [ Reachy Mini Lite](https://www.seeedstudio.com/Reachy-Mini-Lite-Kit-p-6702.html?sensecap_affiliate=bWJooAR&referring_service=link), the small expressive robot from Pollen Robotics.\n\nReachy provides something a touchscreen cannot: **physical presence**.\n\nIts head movement, antennas, voice and reactions make even a relatively simple ordering interaction feel very different from navigating menus on a kiosk.\n\nBut Reachy isn't merely there as an animated mascot.\n\nThe conversation is connected directly to the ordering system.\n\nWhen the customer adds, removes or changes something, Reachy isn't just generating a response - it is affecting the state of a real order.\n\nBeside Reachy is the [ Seeed Studio reTerminal E1003](https://www.seeedstudio.com/reTerminal-E1003-p-6731.html?sensecap_affiliate=bWJooAR&referring_service=link).\n\nThe E1003 is particularly interesting for this project because it combines a large monochrome ePaper display with touch capability.\n\n💡\n\nSeeed Studio discount:If you're interested in the E1003, E1004 or Sticky, you can use codefor an additional discount where eligible.`CFST3GPA`\n\nIn Reachy PizzAIolo, its main job today is **live order review**.\n\nAs the conversation progresses, the display reflects the current state of the basket.\n\nThat matters because voice interfaces have a weakness: **spoken information disappears**.\n\nIf Reachy says:\n\n\"I've added two Margheritas, one sparkling water and a tiramisu...\"\n\nthe customer shouldn't have to remember all of that.\n\nThe E1003 turns the conversation into something persistent and glanceable.\n\nYou can talk to Reachy while still being able to look at the order.\n\nThis also creates the basis for something more interesting later: a genuinely **multimodal ordering experience**, where speaking and touching the display become interchangeable ways of modifying the same order.\n\nAt a high level, the architecture is intentionally straightforward:\n\n```\n       Customer\n          │\n          ▼\n    🤖 Reachy Mini\n          │\n          │ Conversation\n          ▼\n   🧠 Ordering Service / AI\n        │             │\n        │             │\n        ▼             ▼\n 🖥️ reTerminal     🍽️ Active\n     E1003             Orders\n```\n\nThe **ordering service** is the important layer in the middle.\n\nRather than treating the conversation as a stream of unstructured text, it maintains a structured representation of the customer's order.\n\nThat means the same order state can be used by several different interfaces.\n\nReachy can talk about it.\n\nThe E1003 can display it.\n\nThe restaurant dashboard can act on it.\n\nAnd future interfaces could modify exactly the same underlying order.\n\nImagine walking up to Reachy:\n\n**Reachy:**\n\n\"Hi! Welcome. What can I get for you?\"\n\n**Customer:**\n\n\"Can I have two Margheritas and a Coke?\"\n\nThe ordering service extracts the items and quantities and updates the active basket.\n\nThe E1003 now shows:\n\n```\nYOUR ORDER\n\n2 × Margherita\n1 × Coke\n```\n\nThen the customer says:\n\n**Customer:**\n\n\"Actually, change one of the Margheritas to a Diavola.\"\n\nReachy updates the order rather than starting again.\n\n```\nYOUR ORDER\n\n1 × Margherita\n1 × Diavola\n1 × Coke\n```\n\nAnd when the customer is ready:\n\n**Customer:**\n\n\"That's everything.\"\n\nReachy can recap the order and move it into the restaurant's active-order workflow.\n\nThat ability to **modify an existing structured state through natural conversation** is one of the parts I find most interesting.\n\nThe customer-facing interaction is only half of the system.\n\nConfirmed orders are also made available to an **active-orders dashboard**.\n\nThat turns Reachy PizzAIolo from a robot demonstration into the beginning of a restaurant workflow.\n\nThe important distinction is that the AI isn't merely producing a conversation.\n\nIt produces **structured actions that another system can consume**.\n\nThat opens up obvious future integrations with:\n\nThe robot is simply one interface into that system.\n\nDuring this project, I increasingly found that the interesting part wasn't really the robot *or* the screen.\n\nIt was the relationship between them.\n\nIt is very natural to say:\n\n\"Give me another one of those.\"\n\nor:\n\n\"What do you recommend?\"\n\nor:\n\n\"No onions on that one.\"\n\nA screen is much better at answering:\n\nWhat have I ordered?\n\nHow many?\n\nHow much?\n\nWhat choices are available?\n\nSo instead of asking whether **voice or touch** is the better interface, Reachy PizzAIolo explores what happens when each does the job it is naturally good at.\n\nConversation handles intent.\n\nThe sign provides context and confirmation.\n\nThe current prototype implements the core end-to-end experience:\n\nA customer can build and modify an order by speaking naturally with Reachy.\n\nThe customer-facing E1003 reflects the current order as the conversation progresses.\n\nOrders flow through to a separate active-orders view for the restaurant.\n\nMost importantly, these aren't separate demonstrations.\n\nThey are different views onto the **same order state**.\n\nThere are several directions I would like to take this.\n\nAt the moment, conversational turn-taking is more rigid than I ultimately want.\n\nThe next step is allowing the customer to interrupt Reachy naturally:\n\n\"Actually...\"\n\nand immediately correct or extend an order without waiting for the robot to finish speaking, while the system keeps track of the conversation so far.\n\nThat would make the interaction feel significantly closer to talking to a human member of staff.\n\nThe E1003 is touch-enabled, which creates a particularly interesting next step.\n\nImagine Reachy saying:\n\n\"We have four desserts - I've put them on the screen.\"\n\nThe customer could then either say:\n\n\"I'll have the tiramisu.\"\n\n**or simply tap it.**\n\nBoth interactions would manipulate the same underlying order.\n\nConversation when conversation is easiest.\n\nTouch when touch is easier.\n\nNo separate modes.\n\nRestaurant conversations are deceptively complicated.\n\nAn ordering assistant needs to distinguish between actions such as:\n\nI want to continue moving more of this behaviour into explicit, structured **skills/tools**, leaving the language model to understand the conversation while deterministic services handle the actual restaurant operations.\n\nThat should make the system both more capable and more reliable.\n\nAnother direction I am particularly interested in is moving more of the AI stack to the edge.\n\nA future version could use something such as Seeed Studio's [ reComputer Robotics J5012](https://www.seeedstudio.com/reComputer-Robotics-J5012-with-GMSL-extension-board-p-6682.html?sensecap_affiliate=bWJooAR&referring_service=link) as a local AI server for the restaurant.\n\n**To be clear: the J5012 is not part of the current implementation.**\n\nWhat interests me here is not necessarily putting a powerful AI computer behind every robot or display. Instead, a restaurant could potentially have **one local AI machine serving the whole location**.\n\nThat shared edge server could provide services such as speech recognition, text-to-speech, language models and AI orchestration to multiple Reachy or signage endpoints around the restaurant.\n\nThe customer-facing devices could remain relatively lightweight, while the more computationally intensive AI runs centrally within the store.\n\nFor a real deployment, that could offer an interesting balance between local processing and cloud services - potentially improving latency, resilience and privacy without requiring dedicated AI hardware at every ordering point.\n\nDespite the name, there is nothing fundamentally pizza-specific about the architecture.\n\nReachy PizzAIolo is really an experiment in **conversational interactive signage for restaurants**.\n\nThe same pattern could work in:\n\nAnd Reachy doesn't necessarily have to be the final physical interface either.\n\nThe broader idea is a service where **conversation, signage and structured business workflows all share the same state**.\n\nThe pizzaiolo is simply a much more entertaining way to demonstrate it. 🍕\n\nI am making the project available so that the individual components and architecture can be explored and reproduced.\n\n👉 **GitHub:**\n\n[https://github.com/danuw/reachy-pizzaiolo](https://github.com/danuw/reachy-pizzaiolo)\n\nThe repository contains the application code and will continue to receive documentation and setup instructions as I tidy the contest prototype into something easier for others to reproduce.\n\n🤖 **Reachy Mini Lite - the version used in this project**\n\n[Seeed Studio product page – affiliate link](https://www.seeedstudio.com/Reachy-Mini-Lite-Kit-p-6702.html?sensecap_affiliate=bWJooAR&referring_service=link)\n\n📖 **Reachy Mini source and documentation**\n\n[https://github.com/pollen-robotics/reachy_mini](https://github.com/pollen-robotics/reachy_mini)\n\n🤖 **Other embodied AI robots from Seeed Studio**\n\n[Seeed Studio collection – affiliate link](https://www.seeedstudio.com/hugging-face-embodied-ai-robots?sensecap_affiliate=bWJooAR&referring_service=link)\n\n🖥️ **Seeed Studio reTerminal E1003**\n\n[Product page – affiliate link](https://www.seeedstudio.com/reTerminal-E1003-p-6731.html?sensecap_affiliate=bWJooAR&referring_service=link)\n\n🏷️ **Seeed Studio discount code**\n\nUse ** CFST3GPA** for an additional discount on the E1003, E1004 or Sticky where eligible.\n\n📖 **reTerminal E1003 documentation**\n\n[https://wiki.seeedstudio.com/getting_started_with_reterminal_e1003/](https://wiki.seeedstudio.com/getting_started_with_reterminal_e1003/)\n\n🏆 **Seeed Studio Interactive Signage Contest 2026**\n\n[https://www.seeedstudio.com/make-a-sign-interactive-signage-contest-2026](https://www.seeedstudio.com/make-a-sign-interactive-signage-contest-2026)\n\n🎥 **Project video**\n\n[https://youtu.be/t1Ayfm52QaI](https://youtu.be/t1Ayfm52QaI)\n\nI started this project thinking about how to make a restaurant sign interactive.\n\nI ended up asking a slightly different question:\n\nWhat if the sign stopped behaving like a screen and became part of the conversation?\n\nReachy PizzAIolo is still a prototype, but it has already convinced me that conversational AI becomes much more interesting when it escapes the browser.\n\nGiving an AI a physical presence changes the interaction.\n\nGiving the conversation a persistent visual surface makes it more usable.\n\nAnd connecting both of those to a real structured workflow is what starts turning the demonstration into a product.\n\nThere is plenty more I want to explore - particularly full-duplex speech, touch + voice interaction, structured skills and local AI.\n\nBut for now...\n\n**Buon appetito! 🤌🍕🤖**\n\n*This project was created as an entry for the Seeed Studio Interactive Signage Contest 2026. Some links in this article to Seeed Studio products are affiliate links. If you purchase through one of these links, I may receive a small commission at no additional cost to you. Where eligible, you may also be able to use discount code **`CFST3GPA`\n\n** on the E1003, E1004 and Sticky. This does not affect the opinions or technical information presented in this article.*\n\n**Tags:** `#ai`\n\n`#robotics`\n\n`#iot`\n\n`#opensource`", "url": "https://wpnews.pro/news/reachy-pizzaiolo-when-a-restaurant-sign-starts-a-conversation", "canonical_source": "https://dev.to/danuw/reachy-pizzaiolo-when-a-restaurant-sign-starts-a-conversation-4agf", "published_at": "2026-08-24 23:21:02+00:00", "updated_at": "2026-08-24 23:43:38.591411+00:00", "lang": "en", "topics": ["artificial-intelligence", "natural-language-processing", "ai-products", "robotics"], "entities": ["Reachy Mini Lite", "Seeed Studio", "reTerminal E1003", "Pollen Robotics", "Reachy PizzAIolo"], "alternates": {"html": "https://wpnews.pro/news/reachy-pizzaiolo-when-a-restaurant-sign-starts-a-conversation", "markdown": "https://wpnews.pro/news/reachy-pizzaiolo-when-a-restaurant-sign-starts-a-conversation.md", "text": "https://wpnews.pro/news/reachy-pizzaiolo-when-a-restaurant-sign-starts-a-conversation.txt", "jsonld": "https://wpnews.pro/news/reachy-pizzaiolo-when-a-restaurant-sign-starts-a-conversation.jsonld"}}