Altas
Overview:
Personal search index combining users’ activity and behavioral patterns to provide a semantic search, using images and events, as well as insights and automated recommendations. Altas captured each user’s individual behaviors—including both the content and action on a comprehensive timeline. This index could then be searched to recreate moments from your past.
Responsibilities:
Co-founder, responsible for design, user research and product management.
Directed iterative design process to develop search interface, visualizations and index management tools
Defined and drove product vision and detailed roadmap, use cases, wireframes and detailed requirements.
Co-led fundraising for our second round.
Established design language for the product
Deliverables:
Mad-Lib personal search tool for Mac, iOS, and Windows
Comprehensive Design System
Established biweekly User Research cadence
User personas
Collateral and GTM material
Prototyped enterprise solutions
Impact:
Product Design, Branding, Product Strategy & Prioritized Roadmap
Drove Alpha and Beta user programs
Refined & validated business model
Solved the customer trust challenges
Visual Search
Rather than relying on a list format of results, Atlas employed visual search results. Displaying screenshots of the found items. These screen shots could be grouped together by time, topic, people, locations, etc. Atlas would create semantic connections based on loops, topics, location, and routines to capture no only single items, but rather it would capture the entire moment.
Atlas would index everything on the screen while you were working on a task, it would also capture copy/paste events, flipping between windows. Opening a link from an email or message Atlas would track the sender, the other recipients, your reply, and what you did next. Atlas could then take you back to that moment, augmenting your memory and recommending next steps.
Moments
Given Atlas captured running index of all content on your device and actions you took, then stored that information on a timeline. Traditional searches find an item—a message or webpage, they search for needles in a haystack; Atlas was a time machine.
Altas allowed you to easily move from that one message to recreating the moment you first read it—opening that excel file, your browser tabs, related emails, even the music you were listening to.
Altas integrated with OS and internet search tools as well. Since Altas’ index was driven by what the user had done or seen, rather than a general public index driven by popularity or promotional algorithms, Altas’ results were truly personalized and they could remind you of things you may have already read, done, or seen related to that Google or Apple search.
Altas “Sidecar” embedding Atlas results on a Google Search page
OS level notifications could prompt users for related items
Smart search based on your current activity
Recommendations
Once the Altas index was well established, being able to combine the user’s routines with reoccurring areas of interest we could begin to suggest recommendations. Both in terms of related items to their current task, but also people and simple workflows.
Since Atlas ran continuously in the background, it could dynamically model the user’s activity and based on their prior behavior anticipate what the user may want to do next.
Opening Atlas in the middle of a task, would trigger a default search for related items based on content, people, location, etc.
Personas reflected the core Use Cases
The Mad-Lib Search Interface with keyword recommendations
Mad-Lib Search Interface
Another design innovation for Atlas was the use of a mad-lib style search interface. The user could type or select from a set of words or short phrases to focus or expand their search. This allowed the user to search independent of keywords. Once they had returned to the moment in time they were looking for, they could then share the moment with friends and colleagues, or simply pick-up where they left off.
The Mad-Lib style interface allowed users to have discrete control over their search. The Mad-Lib set could also be tailored to spend content types, locations, or different contexts.
Initially, Atlas had a B2C focus, recognizing the need within knowledge workers and professionals to help manage and organize their chaotic lives. However over time it was clear there was an opportunity for Atlas in the B2B space as well, with enterprise knowledge management services and collaboration tools.