Neo: AI-Native Browser

The omnibox gives users a clear choice between navigating, searching, or chatting. Instead of guessing the user's intent, Neo makes the available paths visible, helping AI feel like an added capability rather than a disruption to familiar browser behavior.

Users can add page or selection context directly into side chat, helping them continue the conversation from what they are already viewing instead of starting over or manually copying content.

Composer gives users a lightweight writing surface inside the browser, so they can draft, rewrite, or improve text without switching tools or copying content back and forth.

Snippets let users add saved prompts through shortcuts, making repeated AI tasks faster and more consistent. Instead of retyping the same instructions, users can quickly insert a reusable prompt and keep their workflow moving.

As Neo introduced more AI-powered workflows, users needed a clearer way to return to the things they created, saved, or interacted with. I explored a unified space for browsing history, chat history, generated images, artifacts, bookmarks, and projects.

• Problem: The omnibox had to support more than one intent: navigating to a website, searching the web, or asking AI. If Neo guessed incorrectly, a familiar browser interaction could quickly feel unpredictable.
• Solution: I designed the omnibox to make intent explicit. Users could choose whether they wanted to navigate, search, or chat, preserving the reliability of a traditional browser while opening up AI as a new path.

• Problem: AI responses are only useful when the right context is included, but users often do not know what the AI can see or use. In a browser, this creates trust issues around pages, selections, tabs, and chat history.
• Solution: I explored context controls that made attached sources visible in the side chat. Users could add page or selection context, understand what was being referenced, and include or exclude context from the conversation.

• Problem: When users wanted help drafting or improving text, they had to move between the page, chat, and the input field. That copy-paste loop made AI assistance feel separate from the actual work.
• Solution: Composer introduced a lightweight writing surface inside the browser. Users could draft, rewrite, or improve text in place, keeping AI support close to where the writing was happening.

• Problem: Many AI workflows depend on repeated instructions: summarize this, rewrite in this tone, extract key points, compare options. Rewriting those prompts every time slowed users down, and users often struggled to discover effective prompts in the first place.
• Solution: I designed a Snippets Gallery where users could browse, save, and reuse curated prompts for common tasks. The gallery helped users get started faster, improve consistency, and unlock more value from AI across everyday browsing tasks.

• Problem: As users browsed, chatted, generated images, created artifacts, saved bookmarks, and organized projects, their work could become scattered across the product.
• Solution: I explored a unified space that brought these saved and generated items together, helping users understand the relationship between browsing activity, AI conversations, and saved outputs.

• Problem: Neo was not just introducing AI features; it was redefining how AI fit within a browser. Core browser experiences such as navigation, tabs, and page interactions needed to coexist with newer AI workflows.
• Solution: I helped establish interaction patterns that connected browser fundamentals with AI capabilities, aligning behaviors across the omnibox, side chat, composer, snippets, and saved activity while respecting familiar browser conventions.