AI Studio · Audit & Build

A chatbot that admits when it doesn’t know — and logs the question so it knows next time

This family entertainment and childcare brand started with an AI Studio Audit to evaluate where AI and automation could actually address its customer-service challenge without compromising the guest experience.

Sector
Family entertainment & childcare, resort-casino locations
Engagement
AI Studio Audit + Build
Where the audit pointed

A chatbot, not another headcount

The audit pointed to an AI-powered chatbot: a way to give guests immediate answers to common questions while reducing the routine inquiries reaching the contact form.

What we built

A knowledge source the client actually controls

From there, we built a chatbot connected to a controlled knowledge source — the client’s own approved information, not the open web. Response language was written to sound like a real person answering, not a script reciting information, so the experience felt like getting help rather than filling out a form.

The guardrails

Turning gaps into a to-do list, not a dead end

Specific guardrails required the chatbot to rely only on approved data. If it didn’t have enough information to answer confidently, it was directed to say so, point the guest toward a real person, and log the question so the client could add the answer for next time. That turned gaps in the knowledge base into a running to-do list instead of a dead end.

Chatbot confidence-gated response workflow A guest question is checked against an approved knowledge base. If the bot is confident, it answers directly. If not, it tells the guest, points them to a person, and logs the question, which feeds back into the knowledge base over time. Guest asks a question Checks approved knowledge base Not the open web Confident enough to answer? Yes No Answers directly Sounds human, not scripted Flags a human & logs it Adds the gap for next time Knowledge base grows Teal = direct answer · Purple = escalate and log
The confidence check that runs on every question the chatbot receives.
What it does now

From answering questions to surfacing the right offer

Once location information, pricing, hours, policies, FAQs, and current promotions were loaded in, the chatbot started doing more than answering basic questions. When a guest mentioned when and where they planned to visit, it could surface relevant promotions or events at that location and time — turning a simple question about hours or pricing into an opportunity to mention an offer the guest might otherwise have missed.

The result

Fewer routine tickets, more time for the ones that need a person

The result was a better experience on both sides of the conversation. Guests could get answers to common questions 24/7 instead of waiting for someone to respond to a contact form. At the same time, fewer routine questions were submitted through the form, freeing staff from repeatedly answering questions already covered elsewhere on the site and giving them more time to focus on inquiries that actually required human assistance.

How much of your routine support volume could a chatbot absorb?

One audit, a clear recommendation, and a build scoped around your guardrails — not a template.

Brandaify
Privacy Overview

This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognising you when you return to our website and helping our team to understand which sections of the website you find most interesting and useful.