PRODUCT DESIGN · CONVERSATIONAL AI · BREEZEWAY

AI Concierge

Designing an AI guest assistant that knows when to answer, when to ask, and when to hand off to a human.

Role: Design Lead  ·  Scope: Strategy, system design, conversation design, UI  ·  Platform: Guest guidebook web app + Breezeway operations platform
AI Concierge — home and recommendations
THE PROBLEM

A static guidebook in a 24/7 business

Vacation rental guests have needs at all hours — WiFi passwords, broken TVs, dinner recommendations, the occasional emergency. Breezeway's Guide gave them static documentation; for everything else they texted the property manager. Every "where are the towels?" message pulled an operator away from real work, and every unanswered question was invisible: there was no structured way to learn what guests couldn't find.

The brief: turn Guide from a reference document into a digital concierge — one guests trust and property managers control.

"The hardest design problem wasn't making the AI answer — it was making it know when not to."
THE SYSTEM

One front door, five flows

Every guest message routes through an intent classifier into one of five purpose-built flows — Question, Issue, Request, Recommendation, Emergency — with a sixth path for unclear messages that asks a clarifying question instead of guessing. Designing the routing layer first kept every downstream flow honest: each solves one guest job, with its own data sources, escalation rules, and tone.

AI Concierge — Intent ClassificationEvery guest message routes through one front door. Unclear intent never gets guessed — it loops back with a clarifying question.Guest opens GuideAI Concierge entrypersistent on every pageGuest opens chatGreeting +quick-start promptsGuest sends a messageINTENTCLASSIFICATIONQuestionQUESTION FLOWanswer with confidenceIssueISSUE FLOWtroubleshoot → taskRequestREQUEST FLOWlocate or fulfillRecommendationRECOMMENDATIONcurated + bookableEmergencyEMERGENCY FLOW911 first, PM auto-alertUnclearCLARIFYask, then re-route
The intent classification flow. Unclear intent never gets guessed — it loops back with a clarifying question.
AI Concierge — System at a GlanceFive flows, three guarantees: never bluff, never dead-end, always close the loop.QUESTION"What's the WiFi password?"Search Guide +property dataConfident?confidence check before answeringYes → answerinstantly + source linkNo → hand offto PM + log gapin activity feedISSUE"The bedroom TV won't turn on"Guide guest throughtroubleshooting stepsResolved?if not: collect details + photosCreate Breezeway taskentry permission + timing confirmed,urgent issues auto-prioritizedREQUEST"We need more towels"Already on-site?check before dispatching anyoneYes → pointto locationNo → collectdetails, createtaskRECOMMENDATION"Where should we eat tonight?"PM-curated picks +Google Places searchTop 3 with ratingsbook a table or arrange a ride in-chat;no results → PM notified of content gapEMERGENCY"Smoke coming from the kitchen"Call 911 — shown firstno search, no pleasantriesPM contact + auto-escalation,extinguisher + exit locationssurfaced in parallelGUEST HELPED — every path terminates hereThen, and only then: a contextual upsell — hot tub instructions, beach kit, late checkout, kayak tour. Helpful first, commercial second.The self-improving loopEvery low-confidence answer and missing recommendation logs acontent gap to the PM's activity feed — the knowledge baseimproves with every miss.Proactive, not just reactiveOn day 3, the AI checks in unprompted — pairs the weather forecastwith bookable local activities and reserves them in-chat.Support channel becomes an experience (and revenue) channel.
Five flows, three guarantees: never bluff, never dead-end, always close the loop.
PRINCIPLE 01

Confidence before answers

When the AI is confident, it just answers. A guest asking for the WiFi network gets the name and password in one tap, with a source link back into Guide to verify — no operator pulled away from real work. The scoring is what makes this safe: every retrieval is rated before the AI speaks, so a high-confidence answer like this is only ever shown when the system actually knows. When confidence is low it does the opposite — says so plainly, offers to check with the property manager, and logs a content gap. Property managers set the threshold and the tone. The screens below show the high-confidence path end to end.

Scroll to see the full flow
PRINCIPLE 02

Escalation is a feature, not a failure

Issues start with guided troubleshooting. When that fails, the conversation doesn't dead-end — the AI collects details and photos, confirms entry permission and timing, summarizes for the guest to confirm, then creates a fully-specified task in Breezeway. The ops team sees the task and full context in the messaging thread; the guest never repeats themselves. Urgent issues ("no hot water, ASAP") are auto-prioritized with an immediate PM alert.

Scroll to see the full flow
PRINCIPLE 03

Emergencies break all the rules

"There's smoke coming from the kitchen" is not a conversation. The Emergency flow inverts everything: no search, no pleasantries. Call 911 first, then the PM's direct line, extinguisher and exit locations — while the property manager is auto-alerted in parallel, without being asked.

Scroll to see the full flow
PRINCIPLE 04

Guardrails guests never see

Trust is mostly invisible. The AI may only draw from the property's Guide, Property Profile, and Blueprint — internal team notes are never surfaced, and access-code visibility rules are enforced so a door code can't leak before check-in day. Recommendations stay PM-curated (enriched with Google Places ratings and details) rather than open web search, keeping property managers in control of what their guests are told.

PRINCIPLE 06

The right list, not a long one

A guest asking “any good places nearby?” doesn’t want a directory — they want the right answer. The AI narrows by intent first (what are you in the mood for, then what kind of food) before it recommends anything. Results blend two sources the guest never has to think about: the host’s own curated picks and live Google data — ratings, distance, hours — so a property manager’s favorite local spot sits alongside the highest-rated option down the street. The guest gets a recommendation that feels personal and current; the host gets to put a thumb on the scale without it reading like an ad.

Scroll to see the full flow
PRINCIPLE 05

Revenue without over stepping

Every flow has a designed upsell moment — strictly after the guest's need is met. Answer the WiFi question, then mention the hot tub. Solve the towel request, then offer the beach kit. Book the repair, then offer late checkout. On day 3, the AI proactively checks in, pairs the weather forecast with bookable local activities, and reserves them in-chat. Helpful first, commercial second — that ordering is what makes guests say yes.

Scroll to see the full flow
MEASUREMENT

Designed to be measured

I mapped nine canonical interactions — from a WiFi question to a kitchen fire — into a behavior matrix covering trigger, first action, data source, resolution type, upsell, PM involvement, task creation, and logging. It became the team's source of truth for scoping and the rubric for AI evaluation, paired with a full event-tracking spec (sessions, intent detection, flow completion and abandonment, response confidence, link clicks).

Self-service rate

% of guest questions resolved in Guide without escalation

Escalation quality

Fewer follow-ups needed after an issue reaches the ops team

Speed to resolution

Time from issue report → task assigned → staff dispatched

Content health

AI-surfaced Guide gaps reviewed and fixed by admins

REFLECTION

Designing for fallibility

The most important moments I designed weren't the happy paths — they were the moments the system says "I'm not sure," hands off gracefully, and leaves the guest more confident, not less. Trust isn't built by the answers; it's built by what happens when there isn't one.