PROJECT SUMMARY
Blockit is an AI scheduling assistant that negotiates meetings on your behalf by understanding your calendar, preferences, and communication patterns. Instead of sending links or coordinating availability manually, the agent learns how you schedule and handles the back-and-forth automatically. The challenge was helping new users understand how to collaborate with an AI agent while getting them into the product quickly. The onboarding flow needed to teach users how the assistant works, gather the context the agent requires to operate successfully, and build trust—without overwhelming them with setup steps.
The Big PICture
Design principles
We developed a set of onboarding principles to guide the experience:
1. Educate through interaction
Rather than explaining the product with long tutorials, onboarding introduces concepts as users configure their assistant. Each step teaches how the agent thinks about scheduling.
2. Capture the minimum context for success
The agent needs key information—calendar access, scheduling preferences, and meeting priorities—to operate reliably. The flow focuses on collecting only what is necessary to enable meaningful automation.
3. Move users to value quickly
The fastest way to understand an AI agent is to use it. Onboarding guides users to their first scheduling action as quickly as possible.
Another important consideration was maintaining a high level of visual polish throughout the experience. AI products can easily feel unpredictable or opaque, so craft plays an important role in establishing trust. Careful attention to typography, layout, motion, and micro-interactions helped communicate clarity and reliability while the system explained what it was doing. The goal was to make the product feel thoughtful and deliberate—because when users are learning how to work with an AI agent, the quality of the interface strongly shapes how they perceive the intelligence and capability of the system itself.
final thoughts
Outcome
The redesigned onboarding flow helps users understand the role of the scheduling agent, configure the essential context it needs, and reach their first successful scheduling interaction within minutes. By balancing education, configuration, and speed, the experience turns a complex AI system into something users can trust and start using immediately.
