MyAviator, OpenText | 2024.07 - 2025.06
An AI assistant that turns document-heavy work into instant summaries, PII detection, translations, and podcasts.
Team: 1 Product Designer,
3 PMs, 12 Engineers
My Role: Research,
Design & Prototyping
I led the UX for MyAviator at OpenText, a single place where users upload documents, analyze them with AI, and act on the results without switching tools. I took it from early workflow definition to MVP launch, designing the Space model, the file interactions, the AI action flows, and the end to end experience across summarization, PII detection, translation, and podcasts.
Key metrics post launch
Daily active users
250+
Total documents processed in first month
18,500+
AI actions triggered
42,000+
User Satisfaction rating
4.3/5
— Context
What is MyAviator?
MyAviator is a standalone AI assistant at OpenText, built for enterprise teams who live in documents: HR, support, compliance. Instead of moving a file between a summarizer, a translator, and a redaction tool, they do all of it in one workspace, with answers grounded in the files they uploaded.
— Opportunity
Documents were everywhere. AI was not.
Enterprise users worked with large volumes of documents every day, yet AI support was tied to individual products. There was no single place to upload files, combine information, and take action across them. Users switched tools, repeated steps, and manually reviewed content, which slowed down their work.
Signals from internal discussions and product reviews showed
80%
Users switch between 3 or more tools to complete single task involving documents.
65%+
of daily tasks involved document review or analysis
— Research results & insights
What users told us
Through 40 survey responses and follow up discussions with HR and Support teams, we identified key patterns in document heavy workflows.
“I have to open three tools just to compile one report.”
1. Document work spans multiple tools
Users switch between platforms to review, summarize, redact, and share files. There is no single place to complete document tasks end to end.
2. Early stage document review is manual
Many users manually read and combine information from multiple files before making decisions. This step takes time and often involves repetitive copying and formatting.
“I still have to read everything myself before I can act on it.”
3. Sensitive data handling is a manual step
Users regularly work with documents that contain sensitive information, yet redaction and compliance checks are done manually.
“We handle confidential data often, and redacting it is still a manual task.”
— HMW Statement
How might we create a single workspace where users can upload multiple documents, extract insights, and perform actions without switching between tools?
— User Journey
Mapping the document workflow with MyAviator
I mapped the end to end document workflow to understand how users upload, review, summarize, redact, and share files. This helped us identify where manual effort and tool switching slowed them down.
— Scoping
Where we chose to focus?
Based on the document workflow and research insights, we focused MyAviator on the two most critical stages in document handling.
Review Stage
How might we help users quickly understand large sets of documents without manually reading everything?
Action Stage
How might we make it effortless for users to summarize, redact, translate, and export documents in one place?
Why didn’t we build it as a general AI chatbot? Users are familiar with conversational AI. So why not make MyAviator fully open ended?
From a product perspective
Users needed focused actions on selected documents, not endless chat.
So we built a context driven workspace instead of a generic assistant.
From a User perspective
Users needed focused actions on the documents they chose, not an open-ended chat. So we built a context-driven workspace instead of a generic assistant
— Solution #1 - Guided Actions
Improving first-try output quality
One key issue users faced was inconsistent results when asking open ended questions across multiple documents.
To solve this, I introduced predefined document actions for common tasks like summarizing files, detecting sensitive data, translating content, and generating podcasts.
Instead of crafting complex prompts, users could select a structured action and get more accurate results on the first try.
— Solution #2 - Spaces
Creating context before action
One major challenge users faced was losing context while working across multiple files. Conversations felt disconnected, and results varied depending on what was selected.
To solve this, I introduced Spaces as focused work environments. Users create a Space, upload related documents, and perform actions directly on those files.
Each Space maintains its own context. This ensures responses are grounded in a defined document set, improving relevance, consistency, and control.
— Solution #3 - Multi File Intelligence
Understanding documents together
Users were manually comparing information across multiple files, which increased cognitive load and time spent switching contexts.
I designed MyAviator to support cross document analysis, allowing users to run actions on selected files simultaneously. This reduced manual compilation and improved information synthesis within a single interaction flow.
— Solution #4 - Mobile Version
Designed for on the go use
Mobile usage showed a different pattern. Users were not uploading documents or managing Spaces. They were consuming outputs while commuting.
I adapted the mobile experience to prioritize audio summaries and saved content, allowing users to listen to generated podcasts while traveling.
The goal was simple. Make MyAviator useful even when users are away from their desks.
Mobile is built for consumption, not creation.
Users can instantly listen to insights or revisit saved items. no setup needed.
Optimized for quick sessions.
Open → Resume → Listen.
No heavy workflows, no distractions.
— Reflection
What I learned from this project
Designing MyAviator helped me understand what it means to build AI inside real enterprise constraints. Accuracy, privacy, and reliability are not optional. Every design decision had to balance user needs with system limitations.
I also learned how important it is to define scope early and align closely with engineering to avoid over promising on AI capabilities.
✅ What went well:
Clarified complex document workflows early, reducing scope debates and stakeholder misalignment
Maintained close collaboration with product and engineering throughout evolving scope discussions
⚠️ What could be improved:
Overestimated AI capability in early exploration. A title suggestion feature produced low relevance results and was removed after validation.
Did not prioritize onboarding early enough, which impacted first time user clarity and feature adoption.