What problem does it solve?
Museums, heritage sites, cities and events hold far more knowledge than a visitor ever sees. Wall labels are short, recorded audio guides cover a fixed route in a handful of languages, and human guides are limited by schedules, group sizes and the languages they speak. Visitors who are curious but not experts, who speak another language, or who cannot read small print or see the object well get the thinnest experience. National Gallery Singapore puts it plainly: people walking into a museum often feel lost or intimidated.
Updating guide content is slow as well. Every new exhibition, route or audience (children, specialists, first time visitors) means rewriting and rerecording the same stories. Tourism boards face the same problem at city scale, with visitor questions arriving in dozens of languages and outside office hours. A generative guide changes the unit of work: curators maintain one body of approved content, and the guide tells it in the visitor's language, at the visitor's level, about the thing in front of them.
- UN Tourism estimates that 1.52 billion international tourists were recorded worldwide in 2025, almost 60 million more than in 2024.UN Tourism World Tourism Barometer (2026)
How does it work?
- Know where the visitor is. The guide receives context with each question: the room or stop, a GPS position, a QR code or object number, or a photo of the artwork that is matched against the collection (Art Basel's Lens returns artist and gallery details in about two seconds).
- Retrieve approved content. It looks up the object or place in the collection database or points of interest list and retrieves the curated texts, research and practical information (opening hours, accessibility, routes) that belong to it.
- Tell the story in the visitor's terms. The model turns that content into a short spoken or written answer in the visitor's language and at their level, and can connect it to interests the visitor mentions, as National Gallery Singapore's G(ai)le does with pop culture references.
- Answer follow up questions. Visitors ask in their own words, by voice or text; the guide stays within the approved content and says so when it does not know.
- Suggest what next. It recommends the next stop, event or exhibit based on the visitor's position, time and interests.
- Feed insight back. Anonymized questions show curators and marketing teams what visitors actually want to know, and where the content has gaps.
- Audience
- Customer facing
- Autonomy
- Autonomous
- Adoption
- Early adopters
- Channels
- Mobile app, Web chat, WhatsApp, Phone and voice, Kiosk and branch, Digital human
What is it worth?
Benchmarks are computed from the public deployments below: one data point per organization per KPI, with who made each claim.
| KPI | Median | Reported range | Data points | Claimed by |
|---|---|---|---|---|
| Users served | Not pooled | 10,000 to 17,000 | 2 | 1 organization, 1 vendor |
Value drivers: Customer experience, Inclusion and access, Revenue growth, Employee productivity.
Indicative value
A city museum with 1 million visitors a year and a guided route of about 150 stops
USD 10,000 to USD 200,000
Multilingual guide content production cost avoided per year
How this is calculated
Formula: stops * languages * costPerStopLanguage * refreshShare. The low scenario uses every low input, the high scenario every high input.
| Input | Low | High | Basis |
|---|---|---|---|
| Stops or objects with guide content stops, stops | 100 | 200 | Editorial assumption for a medium sized museum or city route. Replace with your own. |
| Additional languages offered languages, languages | 4 | 8 | Editorial assumption. For comparison, National Gallery Singapore's guide supports four languages in total. Replace with your own visitor language mix. |
| Cost to write, translate and record one stop in one language costPerStopLanguage, USD per stop per language | 100 | 250 | Editorial assumption for professional translation and voice recording. Replace with your own agency rates. |
| Share of stops rewritten or added each year refreshShare, fraction of stops per year | 0.25 | 0.5 | Editorial assumption covering new exhibitions, rotations and audience versions. |
What it leaves out: Counts only the avoided cost of writing, translating and recording guide content in extra languages. It leaves out the cost of running the AI and curating the source content, any revenue from longer visits, return visits or bookings, and the accessibility benefit, which is the main reason many institutions build a guide.
Who already uses it?
13 public deployments, strongest evidence first. Grades: A regulator or audit, B the organization itself, C vendor case study, D anonymous or estimate.
Liverpool City Region Destination Partnership
United Kingdom · Travel and hospitality · 2026
In April 2026 the Liverpool City Region Destination Partnership, supported by the Liverpool City Region Combined Authority, placed an AI digital human named Jimmy at Southport Station to greet visitors before The Open Golf Championship. Jimmy answers questions on transport, events and local attractions across the six areas of the City Region, replies in the language he is spoken to (the release says 99 languages), and can be reached from a phone through a QR code. He stays at the station until August 2026, and the partnership will use the questions he receives to shape visitor services.
No outcome disclosed.
Leeds Castle
United Kingdom · Media and entertainment · 2026
In March 2026 Leeds Castle in Kent added an AI avatar of Eleanor of Castile, the medieval queen who was the castle's first female owner, as the last stop of its exhibition Pilgrimage of Love. Visitors speak to the avatar, which notices when they approach, answers their questions about her life, decisions and legacy in real time, and speaks English, French and Spanish. It runs on SKC Studios' conversational platform 1956 Individuals and draws on the exhibition research of the castle's curators. The castle's heritage director says it lets visitors ask questions curators did not anticipate. No usage or visitor satisfaction figures are published.
No outcome disclosed.
Art Basel
Switzerland · Media and entertainment · 2025
Art Basel's Companion app combines a conversational AI companion, grounded in gallery, artwork, dining and lodging information for its fairs in five cities, with the Art Basel Lens: a visitor photographs an artwork and receives artist and gallery details in about two seconds, matched by image embeddings against a vector index. Art Basel reports more engagement, return visits and time in the app, without publishing figures, and is exploring wayfinding and restaurant bookings.
No outcome disclosed.
Elliott Museum
United States · Media and entertainment · 2025
The Elliott Museum in Florida runs a holographic AI avatar of the archaeologist Howard Carter, built by RAVATAR and announced by the vendor in October 2025. Housed in an interactive holographic display, the avatar talks with visitors in real time about the discovery of Tutankhamun's tomb and answers their questions. The vendor built its knowledge base on Carter's personal writings and verified historical sources, and the museum's chief executive praises the work. The vendor says visitors call the experience inspiring; no usage figures are published.
No outcome disclosed.
Museo Miraflores
Guatemala · Media and entertainment · 2025
Museo Miraflores, an archaeological museum at the Kaminaljuyú site in Guatemala City, had retired its 2021 handheld audio guide devices to an archive room by 2024 over high cost and slow content updates. In 2025 director Maria Gadsden brought in Musa, a location aware AI audio guide, launching it as a paid, permanent guide in about eight weeks, including a four week pilot. Musa's own case study reports roughly 5 times higher uptake than the previous handheld devices and average tour sessions over 40 minutes, at a museum with 120,000 annual visitors. Gadsden says all visitors now prefer Musa to the traditional audio guide.
No outcome disclosed.
National Gallery Singapore
Singapore · Government and public sector · 2025
National Gallery Singapore built G(ai)le, an AI docent that searches the Gallery's archives and explains artworks to visitors in conversational language, in English, Mandarin, Malay and Tamil. It adapts its stories to interests a visitor mentions, offers an audio only mode and an "eyes up" mode, and gives the Gallery a view of what visitors ask about. Staff also use it to draft versions of tour content for different audiences, which writers then refine.
No outcome disclosed.
Schladming-Dachstein Tourist Board
Austria · Travel and hospitality · 2025
For one month in spring 2025 the Schladming-Dachstein Tourist Board tested an AI avatar named Patrizia in its tourist information office, on loan from the Austrian Tourist Board. Guests chose a language on the screen and spoke to the avatar, which was given current regional information about spring hikes and valley walks. The board treats it as digital support next to staff and not a replacement. Guests were hesitant at first, and the test showed that precise background data is needed to avoid hallucinations, with restaurant information as a weak spot.
No outcome disclosed.
Bloomberg Connects
United States · Media and entertainment · 2024
Bloomberg Connects uses Gemini to help create immersive audio guides, with the stated aim of making museums more accessible to visually impaired visitors. Google Cloud's listing gives no detail on scale, languages or results.
No outcome disclosed.
Madrid Destino
Spain · Government and public sector · 2024
Madrid Destino, the city's municipal tourism office, runs VisitMadridGPT, a virtual assistant that answers visitors in more than 95 languages from the city's official, expert curated tourism site, available when physical offices are closed. The city analyzes the questions to find the most requested topics and adjust its website content. According to the story, Madrid attracted 10.6 million visitors in 2023. Madrid's tourism councillor said after the April 2024 launch that almost 10,000 unique users from 103 countries had used it.
- Users served: about 10,000, from the April 2024 launch to the councillor's announcement at Forbes Travel Summit Madrid 2024
"VisitMadridGPT se lanzó en abril y, desde entonces, ha registrado casi 10.000 usuarios únicos de 103 países como Estados Unidos, Italia o Francia, que la usan para obtener recomendaciones y planes personalizados para visitar Madrid."
Claimed by: organization
Presidency of Religious Affairs at the Grand Mosque and the Prophet's Mosque
Saudi Arabia · Government and public sector · 2024
The Presidency of Religious Affairs at the Grand Mosque in Makkah and the Prophet's Mosque in Madinah operates AI powered robots for worshippers and visitors. Each robot has a touchscreen, a camera and a speaker. It gives directions and information on locations and services inside the mosques, explains how to perform Hajj and Umrah rituals, answers religious questions including fatwas and translates instantly for visitors of other nationalities. A February 2024 report listed 11 languages; a May 2026 report says the robot is in use at both mosques. No usage or accuracy figures have been published.
No outcome disclosed.
Saudi Tourism Authority
Saudi Arabia · Travel and hospitality · 2024
The Saudi Tourism Authority showed a beta version of SARA, a generative AI digital human, at World Travel Market in London in November 2024. She is meant to act as a brand ambassador, travel companion and personal concierge: she remembers earlier questions, asks proactive questions, introduces lesser known destinations and builds customized itineraries in several languages. The authority describes her as the first digital human travel companion built by a national tourism board. No usage or outcome figures were published.
No outcome disclosed.
Visit Qatar
Qatar · Travel and hospitality · 2024
Visit Qatar introduced generative AI into its official visitor platforms in 2024. Its GenAI Trip Concierge combines text, voice, interactive maps, trip planning and a virtual human in one experience, chats in more than 50 languages, builds personalized itineraries and remembers visitor preferences. A companion feature, Qatar Lens, takes a photo of a landmark and returns its name, context, opening hours and practical information. Visit Qatar published no usage or outcome figures.
No outcome disclosed.
Centre Pompidou
France · Media and entertainment · 2022
The Centre Pompidou in Paris replaced a rarely downloaded mobile app with a conversational assistant built by Ask Mona, available in French and English. Before a visit it answers practical questions on the museum website. On site a visitor photographs an artwork, the bot identifies it through visual recognition and replies with audio clips, videos and anecdotes. For the Brancusi exhibition a generative model was trained on curated wall texts and curatorial notes, and the curatorial team approved the content. Ask Mona reports 17,000 users in two months and says 20% of visitors use the tool during their visit.
- Users served: 17,000, in the first two months, as Ask Mona describes it
"17,000 users in just 2 months"
Claimed by: vendor
How do you implement it?
A model agnostic playbook: what to prepare, the order to build in, and what goes wrong.
Data you need
- A collection management or points of interest database with stable identifiers per object or place
- Approved, curated texts per object or place, with an owner and a review date
- Practical visitor information (opening hours, routes, accessibility, events) from one source
- A pronunciation list of names of artists, places and local terms for speech recognition and synthesis
- For image recognition, reference photos of each object and the rights to use them
Systems to integrate
- Collection management system or content management system
- The organization's visitor app, website or kiosk software
- Positioning (GPS, beacons, QR codes) or an image matching service
- Ticketing and events calendar for recommendations and practical questions
- Analytics for anonymized question and usage reporting
Complexity: Medium
The content needs more work than the conversation: a clean collection or points of interest database with identifiers, approved texts per object, rights to use images and research, and a reliable way to know where the visitor is (QR codes, beacons, GPS or image matching). Spoken delivery in a noisy hall and accurate recognition of local names and accents need testing on site.
- 1
Start from the content, not the model
Pick one gallery, route or district and bring its content into shape: an identifier per object or place, the approved texts, practical information and a short brief on tone. The quality of the guide will never exceed the quality of this content.
- 2
Decide how the guide knows where the visitor is
QR codes or object numbers are the most reliable and cheapest. Image matching needs no codes on the wall, but it needs reference photos and tests in real lighting and angles; GPS works outdoors but not between rooms. Many deployments use two methods with a fallback.
- 3
Write the voice of the guide
Agree with curators how the guide speaks, what it may interpret and what it must leave open. National Gallery Singapore spent a long time tuning prompts so its docent informs without imposing a single view of the art.
- 4
Test with real visitors and real languages
Build a test set of questions per stop in every supported language, including names that are hard to pronounce and questions the content cannot answer, and run it on every content or model change. Then run a pilot on the floor and listen to what visitors ask.
- 5
Design for access from day one
Offer audio only and large text modes, captions for spoken replies, and a way to use the guide without looking at the screen. These features serve visually impaired visitors and everyone who wants to look at the object rather than a phone.
- 6
Close the loop with curators
Review anonymized questions every month: frequent questions without a good answer become new content, and questions that show confusion feed back into labels and routes.
Guardrails
- Answers only from the approved collection and visitor content, with a clear "I do not know" when the content is silent
- Facts such as dates, attributions and prices are taken from the source record, never generated
- Clear disclosure that the guide is an AI, and a way to reach staff for practical or safety questions
- No identification of people in camera images; image matching limited to objects in the collection
- Location and conversation data kept only as long as needed, anonymized for analytics
KPIs to instrument
- Share of visitors who use the guide, by language and entry point
- Questions per session and share answered from content versus declined
- Factual accuracy on a monthly sample reviewed by curators
- Visitor satisfaction with the guide compared with the recorded audio guide or human tour
- Speech recognition errors on names and local terms, per language
Human in the loop
Curators and educators own the content and the tone of the guide, approve new stories before they go live, and review a sample of conversations each month for errors of fact and tone. Front of house staff handle anything practical the guide cannot, such as lost items, accessibility assistance and safety.
Common failure modes
- Confident but wrong stories
- The guide invents a date, an attribution or an anecdote that sounds right. Prevent with retrieval from approved records, facts taken from structured fields and curator review of samples.
- Wrong object, wrong story
- Image matching or positioning picks the neighboring object and the guide tells the wrong story. Set a confidence threshold and ask the visitor to confirm or scan the code when unsure.
- A screen between visitor and art
- Visitors stare at their phones instead of the object. Design audio first and short answers, as National Gallery Singapore did with its "eyes up" mode.
- Stale practical information
- Opening hours, closed rooms or event times in the guide differ from reality. Pull practical information from one live source instead of copying it into the content.
What are the risks and rules?
EU AI Act
Limited risk (transparency)
A visitor facing assistant must make clear that people are interacting with AI (Article 50), and synthetic speech should be identifiable as AI generated. It is not high risk. It would change if the camera feature were used to identify or categorize visitors by biometric data, which a guide does not need: remote biometric identification, biometric categorization and emotion recognition are high risk under Annex III point 1, and biometric categorization that infers sensitive traits is prohibited under Article 5.
Guidance
- Article 50, transparency obligations for providers and deployers of certain AI systems (European Union, Europe). People must be informed that they are interacting with an AI system, and providers of systems that generate synthetic audio must mark it in a machine readable format as artificially generated.
- Guidelines 02/2021 on virtual voice assistants (European Data Protection Board, Europe). How GDPR applies to voice assistants, including transparency, purpose limitation and retention of voice recordings.
Controls to put in place
- AI disclosure at the start of every session and on spoken replies
- Content ownership per object or place, with review dates and a change log
- Test set per stop and language, run before every content or model change
- Data protection impact assessment covering location data, voice and camera images
- Retention limits and anonymization for conversation logs used in analytics
Frequently asked questions
- Does an AI guide replace human guides and docents?
In the deployments on this page, no. National Gallery Singapore describes its AI docent as a new teammate alongside the tours team, and uses it to draft tour versions that staff refine. The Gallery notes that in person tours are not always available in the language a visitor prefers, which is where the guide helps.
- How does the guide know which object or place the visitor means?
Through context sent with each question: a QR code or object number, GPS outdoors, or image recognition. Art Basel matches a photo of an artwork against its index and returns the artist and gallery in about two seconds. Codes are the most reliable; image matching needs reference photos and a confidence threshold.
- How do you stop the guide from making up facts about the collection?
Ground every answer in approved records, take hard facts such as dates and attributions from structured fields, make the guide say when the content is silent, and have curators review a sample of conversations every month.
- Is an AI tour guide high risk under the EU AI Act?
Not as described here. It carries the Article 50 transparency duties: visitors must know it is an AI, and synthetic speech must be identifiable. Location, voice and camera data still fall under the GDPR, so a data protection impact assessment is advisable. Using the camera to identify or categorize visitors would change the assessment.
How to cite this page
Blits.ai AI Use Case Library, "AI visitor and tour guide for cities, museums and events", last verified 26 September 2026, https://www.blits.ai/ai-use-cases/ai-visitor-and-tour-guide. Licensed under CC BY 4.0. Method: how we verify use cases.
Changelog
- 14 October 2026: Added deployments: Presidency of Religious Affairs at the Grand Mosque and the Prophet's Mosque.
- 14 October 2026: Added deployments: Schladming-Dachstein Tourist Board, Liverpool City Region Destination Partnership, Saudi Tourism Authority, Visit Qatar, Leeds Castle, Elliott Museum.
- 13 October 2026: Added a measured result from Madrid Destino.
- 13 October 2026: Added deployments: Centre Pompidou.
- 1 October 2026: Added deployments: Museo Miraflores.
- 27 September 2026: First published