An AI travel planner built for a travel company plans day-by-day trips only from that company's own products and live supplier availability, and quotes every price with its source. A consultant or the customer confirms the booking.
All Travel & Tourism →
Consumer AI trip planners are good at sketching a trip and bad at the details that matter on the day: whether the museum opens on a Monday, whether the train arrives before the transfer leaves, what the room costs this week. They have no inventory, so every suggestion is a guess the traveller has to check.
An itinerary agent for an operator or agency works the other way round. It can only propose products the company sells or can source: its own tours, contracted hotels, transfers, and live results from supplier APIs such as a GDS, an NDC feed or a bedbank. Every line in the itinerary carries where the price came from and when it was checked, so the consultant can stand behind it.
dates, budget, pace, interests
own products and contracted suppliers
GDS, NDC, bedbank, operator APIs
every price with source and time
through the existing booking flow
packages, special requests, low confidence
General assistants usually do not, because they have no access to live inventory. A planner connected to a travel company's catalogue and supplier APIs does, and that is what we build for operators and agencies: each price in the itinerary is fetched from a source at the time of quoting, with the timestamp kept so it can be re-checked before booking.
Only as accurate as their sources. A model planning from memory will get opening times, distances and prices wrong often enough that every plan needs checking. Grounding the agent in the company's own product data and live supplier results removes most of those errors, and we test it on real past enquiries before it faces customers. It still hands unusual requests to a consultant.
Yes, as long as the same rules apply: it only proposes what the company can sell, it shows that it is an automated assistant, and booking runs through the normal checkout. Many companies start with consultants using it internally, then open it to customers once the evaluation results are good enough.
What we built, what stage it is at, and a link to the live thing wherever there is one.
yourOS is an operating system with an AI at its heart. You talk to it like a person, out loud or typed. It makes your calls, plans your days and works on your projects with a crew of agents, on your own private server. Our own product, built from the first commit; the waitlist is open.
Website, backend and app assets for Sonora, a free AI sound-therapy app on iOS and Android published by Cognitive AI.
Brand, website, prototype, apps on five platforms, the AI backend and the algorithm-intelligence pipeline for Podswap, a social growth engine that runs without a human in the loop.
In closed beta: Roxy, a private AI assistant with permanent memory running on infrastructure the user owns. Brand, site, product, backend and conversational design.
Live at coherence.com: brand identity generated with AI agents we directed, the motion system and website for the group behind Sonora, AboutAI, WakeUp and MudShadows. Agent work remains in build.
Live at domainbooth.com for DomainBooth, a premium domain brokerage: a new animated mark, every page redesigned and rebuilt with designed mobile layouts, and a custom CMS for its sales record, featured names, press and enquiries.
Bring a handful of real enquiries. We will show what the agent would have quoted, from which sources.
30-minute technical call · no deck