AI chatbot for Internal knowledge
Healthcare
Employees across Optum frequently struggle to find accurate, up-to-date answers to commonly asked internal questions related to tools, programs, and operational workflows. Existing knowledge repositories like Confluence or static documents are fragmented, hard to navigate, and often require SME intervention for even basic queries.
Client
United Healthcare
Services
Visual Design
UI & UX Design
Conversational Design
Industries
Healthcare
Insurance
Date
Jan 2025
Context
To streamline onboarding for new employees, reduce reliance on SMEs, and centralize organizational knowledge, Optum needed a way to leverage existing AI endpoints—such as Copilot—while ensuring that the UI and conversational experience were tailored specifically for Optum employees.
The problem
Employees across Optum frequently struggle to find accurate, up-to-date answers to commonly asked internal questions related to tools, programs, and operational workflows. Existing knowledge repositories like Confluence or static documents are fragmented, hard to navigate, and often require SME intervention for even basic queries.
My role
I was the sole product designer on this project, which meant juggling a bunch of roles—from managing stakeholders to working closely with 2+ frontend developers.
Who are the user's
Optum employees across departments and roles who rely on the chatbot to quickly find accurate answers to internal tools, workflows, and process-related queries.
Setting the Stage
before we proceed with exploring options or ideating solutions, we had to get answers to few questions
Why are employees currently struggling to find answers?
Why are existing tools (e.g., Confluence, Copilot) not working well?
Why is it important to solve this problem now?
Who are the most frequent askers of internal questions?
Who are the current information gatekeepers (SMEs, team leads, support teams)?
Who benefits most from instant answers (new joiners, Ops teams, etc.)?
When are delays in finding answers most costly?
What types of questions will the chatbot answer (FAQs, links, SOPs, systems)?
What content sources will it pull from (Confluence, SharePoint, internal wiki)?
What level of personalization is needed (role-based, team-based, geo-specific)?
What success metrics will define its value (time saved, SME load, satisfaction)?
Asking the Experts
Why do we need a chatbot instead of a central repository of documents
What are the most common type of questions employees struggle to get answers?
Which team or department would you think benefit the most from this?
What is the level of personalization you need like role based , team based etc?
How do you wish to roll out this to the team?
What kind of Voice or Tone should Chatbot have to build trust?
Are there any Key KPI’s you want to track?
