MaîtreT
MaîtreT is an AI-powered assistant that transforms the Tock reservation experience.
Problem Space
Problem Statement
How might we reduce booking friction and improve AI accuracy to ensure that Tock minimizes operational inefficiencies and provides a seamless user experience that enhances customer satisfaction?
Problem Background
Tock serves hospitality businesses by providing reservation and guest management solutions. While Tock excels in human-supported service during business hours, their after-hours support relies on a basic chatbot that only collects information without resolving immediate user needs. As competitors like OpenTable and Resy implement sophisticated AI solutions for 24/7 support, Tock users face increasing friction points, particularly during peak dining hours and weekends.
Problem Discovery (Origin of the Problem)
It’s Friday night, and you’re trying to get a last-minute table at a top restaurant. You open Tock, only to find:
- No real-time table availability updates—you're left guessing.
- Waitlist confusion—you have no idea if a spot will open up.
- A chatbot that collects your request but doesn’t act—you’re left waiting.
What do you do? You switch to a competitor, where you can instantly check availability and book. This is the challenge Tock is facing. Today's diners expect instant, AI-powered convenience. Yet, Tock’s current system creates friction, particularly for:
- Last-minute diners who need quick availability updates.
- Users making modifications must cancel and rebook from scratch.
- Restaurants managing peak-hour reservations without real-time AI support.
Why Now?
The market is shifting. Competitors already provide real-time reservation updates and AI-powered phone assistants. If Tock doesn’t evolve, it risks losing users to competitors that offer smarter, faster booking experiences.
Research Insights
User Pain Points
Through extensive user research and competitor analysis, we identified key friction points:
- Users want real-time availability – Manually checking for openings is frustrating.
- Last-minute diners struggle – No waitlist alerts mean missed opportunities.
- Booking modifications are clunky – Users must cancel and restart reservations.
- The chatbot doesn’t solve problems – Collects information but doesn’t take action.
- Competitor AI solutions outperform Tock – Faster responses = higher customer retention.
💡 Big Insight: AI can proactively assist diners, reduce booking friction, and lighten the support workload.
Supporting Data
Research revealed several critical insights about the reservation experience:
- 60% of users dine out at least once a month, making this a frequent need
- Over a third reported booking challenges and required customer support
- Nearly half want more human-like interactions, and 53% want the option to escalate to human agents
Landing on the Solution
After evaluating multiple approaches, including increasing human support, outsourcing customer support, and improving self-service tools, MaîtreT emerged as the optimal solution. The AI-powered assistant addresses all identified pain points while being more scalable and cost-effective than alternatives.
MaîtreT was designed to be context-aware, personalized, and proactive - not just reactive like the current chatbot. The solution focuses on providing real-time information, offering seamless modifications, and maintaining conversation history across channels.
Explanation of Solution
MaîtreT is an AI-powered assistant that transforms the Tock reservation experience.
Unlike the current chatbot, MaîtreT is proactive, providing:
- Real-time table availability – See only bookable tables, no guessing.
- Instant waitlist alerts – Users get notified as soon as a spot opens up.
- Seamless booking modifications – Modify dates, times, and party sizes without canceling.
- AI-driven customer support – A chatbot that actually helps, not just collects data.
- Proactive restaurant assistance – Helps managers optimize availability and guest experiences.
- Human escalation - Seamlessly transfers complex issues to human agents.
User Flows/Mockups
Future Steps
- I’ll continue to work on this product even after the program and move on to a/b testing.
Images - screenshots, marketing assets, etc.
Learnings
Product Manager Learnings:
Adelodun Olusola- Ajayi
- Prompt engineering with Bolt.new
- Experimenting with Bolt.new refined my ability to craft precise prompts, improving how I interact with AI models to get more accurate and relevant responses.
- Understanding LLMs & NLP
- Diving into Large Language Models (LLMs) and Natural Language Processing (NLP) gave me insight into how AI processes language, enhances products, and personalizes user experiences.
- Ethical AI use
- With great power comes great responsibility, and with AI’s growing influence, ethical considerations are crucial. I’ve learned that responsible AI use means ensuring fairness, reducing bias, and understanding the broader impact of AI-driven decisions.
Designer Learnings:
Designer Learnings:
Jo Sturdivant
- Adapting to an Established Team: Joining the team in week 6 of 8 was challenging, as I had to quickly adapt to existing workflows, dynamics, and goals. This mirrors real-world situations where you often integrate into teams mid-project, and flexibility is essential.
- Work-Blocking for Efficiency: With only two weeks to complete the project, I learned the importance of a structured work-blocking system. This approach allowed me to manage my time effectively and meet deadlines under pressure.
- Making Data-Driven Design Decisions: Unlike my past projects, I had to rely on research conducted by others. This was a valuable experience in using pre-existing data to guide design decisions, helping me focus on the core insights without starting from scratch.
Developer Learnings:
Developer Learnings:
Vanady Beard
&
As the back-end developer, I learned how important it is to create efficient and reliable systems that support the entire application. This experience also taught me the importance of optimising the database and ensuring the backend is scalable and easy to maintain.
Developer Learnings:
Stephen Asiedu
&
As a back-end developer, I've come to understand the importance of being familiar with various database systems and modules. This knowledge enables me to build diverse applications and maintain versatility in my work. I've also learned that the responsibility for making the right choices rests on my shoulders, guided by my best judgement.
Developer Learnings:
&
Developer Learnings:
Maurquise Williams
&
- Process of Creating an MVP: Developing a Minimum Viable Product (MVP) taught me how to focus on delivering core functionalities balancing between essential features and avoiding scope creep.
- Collaboration in a Real-World Tech Setting: This experience taught me how to collaborate efficiently in a fast-paced tech environment, keeping the team aligned and productive, even while working remotely across time zones.
- Sharpening Critical Thinking and Problem-Solving Skills: This experience honed my ability to think critically and solve problems efficiently. By tackling challenges and finding quick solutions, I sharpened my decision-making and troubleshooting skills in a dynamic, real-world setting.
Developer Learnings:
Jeremiah Williams
&
All in all this experience was very awesome I learned that in coding with others being transparent is key
Developers Learnings:
Justin Farley
&
I learned how important communication is when working with a team. Communication provides understanding, advice, ideas, and much more. While working with the product team, I’ve found that communication keeps everything flowing smoothly. Working with a team also showed me that every member brings something different to the table and we all have to work together in order to align and meet our end goal.