.gif)
HLabs' First-Ever Chatbot
At HLabs, we’re always ready to take on new challenges. Whether it’s mastering new technology or acquiring new skills, we’re committed to evolving to meet our clients’ needs. So, when we saw an opportunity to break new ground and push our creativity and innovation further into chatbots, we took it.
Our Creative Technologist, Sameer Muley, jumped on the task to lead the project with the vision of transforming traditional quizzes into an interactive chatbot experience that could recommend activities based on user preferences.
Here's a look at how the prototype came to life.
How it started
We are continuously exploring emerging technologies, and chatbots were high on Sameer's radar this year. Among the platforms he experimented with, Voiceflow stood out for its robust capabilities and customisation options. So, it felt like the perfect match for this project's revamp because a chatbot could transform a traditional quiz format into the dynamic, interactive experience we were after.
Building the chatbot
The initial prototype, built with Voiceflow’s AI-controlled responses, took less than a week to set up. Following client feedback, Sameer and the team refined the bot based on detailed requirements.
Airtable, a controlled data system, played a key role in ensuring the chatbot recommended content that met specific criteria, such as the activities’ cost limits and location around London, and even allowed to exclude events outside certain parameters. Its user-friendly interface made it possible to input and manage the extensive data from websites.
By integrating Airtable with Voiceflow, the chatbot could dynamically access this information to provide personalised recommendations to users. This approach not only made the system flexible and scalable but also enabled real-time adjustments to handle evolving data effortlessly.
The entire project, from prototype to final adjustments, was completed in approximately 50-60 days, including rigorous testing.
The challenges
From designing an intuitive conversation flow to meeting strict compliance requirements, the project had its fair share of challenges.
Ensuring the chatbot could understand natural language, including slang and jargon, was a key hurdle. “Balancing functionality with a conversational, human-like feel was challenging,” Sameer explained, “but it taught us a lot about the nuances of conversational design.”
Another primary challenge was setting up filters to exclude content that didn’t meet the criteria. Using Airtable alongside Voiceflow’s Knowledge Base (KB) query API, allowed the team to hone in on relevant content for users, including contextual recommendations based on the time of day. This intricate filtering process underscored the importance of structured data management in chatbot development.
Our takeaways
This project provided valuable insights into improving our approach to chatbot development for future initiatives.
- Agile Development: Starting with a prototype and using Voiceflow’s engagement metrics for iterative improvements allowed the team to refine the chatbot continuously.
- Controlled Data Management: Airtable’s role as a structured knowledge base highlighted the need for reliable, well-organised data.
- Voiceflow’s Functionality: Features like the Knowledge Base API and engagement analytics proved invaluable for maintaining response accuracy and enhancing the user experience.
Reflecting on the project, Sameer shares, “This project showed me the potential for chatbots beyond quizzes — from customer support to product recommendations and even editorial insights. I’m excited to explore more ways to enhance user experiences through conversational technology.”
What’s a Rich Text element?
The rich text element allows you to create and format headings, paragraphs, blockquotes, images, and video all in one place instead of having to add and format them individually. Just double-click and easily create content.
Static and dynamic content editing
A rich text element can be used with static or dynamic content. For static content, just drop it into any page and begin editing. For dynamic content, add a rich text field to any collection and then connect a rich text element to that field in the settings panel. Voila!
How to customize formatting for each rich text
Headings, paragraphs, blockquotes, figures, images, and figure captions can all be styled after a class is added to the rich text element using the "When inside of" nested selector system.
Looking ahead
This chatbot marks the beginning of an exciting new chapter for HLabs. By embracing cutting-edge technology and innovative problem-solving, we’re continuously evolving to meet — and exceed — our clients’ expectations.
Ready to bring your own chatbot vision to life?
Whether you're looking to boost engagement, streamline response times, or deliver a more personalised experience for your users, HLabs can build the chatbot solution you need.
We’ll show ours if you share yours.
Share your details so we can stay in touch and directly show you premium HLabs content!