Built a no-code AI chatbot platform that boosted signups and simplified powerful tech
Overview
I led the design of Easybits’ chatbot builder, which is a no-code web app that helps anyone create and manage AI chatbots, regardless of technical skill. These chatbots are trained using users’ own data, personalized for tone and brand, and deployable across WhatsApp, Telegram, Facebook, or embedded on any website. The goal? To simplify access to complex AI infrastructure, highlight Easybits’ technical capabilities, and support fundraising efforts. The launch helped generate leads and became a tool for closing deals and raising capital
Introduction
Turning complex AI into a usable product
Easybits had developed a flexible and robust AI backend infrastructure capable of supporting intelligent agents in virtually any industry. But to reach real users, they needed a frontend experience that could make AI approachable. Building chatbots using the infrastructure required multiple tools and advanced technical knowledge - out of reach for most of their intended audience, which included busy and non tech-savvy marketers, HR teams, and founders.
As the leading product designer, my task was to turn that complexity into a simple, usable product. With the PMs, Marketers and engineers, we designed a streamlined, no-code platform that allowed teams and individuals to create, train, and manage AI-powered chatbots. The approach kept user needs, business objectives, and tech limitations front and center.
Problems & Challenges
Key challenges and the questions we asked to solve them
The process of building an AI chatbot using easybits’ tools involved multiple steps, tools, and specialized knowledge. Our audience, which ranged from AI-curious entrepreneurs to busy marketing and HR professionals, needed a solution that didn’t assume technical expertise.
So, how might we…
…help users create a chatbot in as few steps as possible?
…reduce the need to leave the app for third-party tools?
…show users how their chatbots are performing and allow for fast iteration?
…highlight easybits’ infrastructure without overwhelming users?
Project Goals
What we aimed to achieve for users and the business
Help users build chatbots confidently
Training and deploying AI chatbots was reserved for developers. Our goal was to make this power available to marketers, HR teams, and founders, with no technical friction.
Showcase business infrastructure
The product had to prove the value of easybits’ backend AI platform to investors and early adopters. Every interaction with the app needed to demonstrate capability and potential at scale.
Give users control over tone and data
Users needed more than just a AI chatbot; they needed one that felt like their brand. We set out to let them train bots with their own data and adjust tone, behavior, and messaging easily.
Solution
Turning complex AI into a usable product, through design
The project began with deep alignment between design, engineering, and business stakeholders. We started by mapping out the technical constraints of easybits’ infrastructure and identifying key user types: from AI-enthusiasts, founders to busy marketing teams. From there, we worked in short cycles to test ideas, validate assumptions, and simplify flows, always balancing flexibility with ease of use every step of the way. At some points, we had users over to test the product and give feedback before and after production.
Product's core functionality
Chatbot Creation Flow
Over five iterations, we refined a guided, step-by-step flow. It allowed users to create functional bots without touching code, while still offering deeper customization where needed.
Customize Data, Variants & Answers
Personalization & Training
Users could train chatbots using their own datasets, control brand voice, add question variants, and fine-tune bot behavior balancing simplicity and power.
Fun fact: at one stage, we didn't have greetings in the chatbot testing phase. We had to make adjustments after a usability testing.
Empower data-driven decisions
In-App Analytics
We designed a clear dashboard that surfaced metrics like message volume over time. This gave users insight into performance and helped guide chatbot improvements.
Results
From prototype to proof of concept
The product launched publicly at app.easybits.tech, generating strong early traction. Sign-ups and qualified leads followed, some of which converted into paying customers. The app also became a critical tool for demonstrating Easybits’ infrastructure during fundraising efforts.
Note: While NDA constraints limit data disclosure, additional details can be shared in a private setting.
Learnings
Simplifying tech is a design superpower
This project sharpened my skills in dashboard UX, designing under technical constraints, and facilitating cross-functional alignment. Designing alongside developers and other stakeholders from day one helped us move faster, avoid rework, and stay grounded in what was possible.
Key Takeaways:
Dashboards aren’t about fancy visuals but about facilitating fast and clear decisions.
Empowering each stakeholder to own their expertise leads to better collaboration.
Constraints aren’t blockers, they’re catalysts for focused, realistic design.
With this lessons, if I revisited past projects, I’d apply this mindset to bring more clarity, utility, and grounded execution into the work.