What looks like a training problem but isn't?
Staff weren't struggling because of low digital literacy, as initially assumed. Through user research, we discovered that the real friction came from fragmented information and inconsistent workflows spread across siloed departments.
The Challenge
As the Whitney transitioned to Microsoft Teams, adoption was inconsistent across departments. The issue was initially framed as a training problem.
After observing workflows and reviewing support requests, I suspected the root cause was something different.
My Role
I helped evaluate technical approaches, define product requirements, structure the knowledge architecture, and design role-aware experiences.
The Insight
Staff often knew what they wanted to accomplish. They simply couldn't find institution-specific guidance when they needed it.
The challenge wasn't training. It was knowledge accessibility.
Key Decisions
- Reframe the problem
Instead of creating more training materials, we focused on delivering contextual guidance directly within existing workflows.
- Design around roles
Different users needed different information. The system was designed to adapt responses based on responsibilities, permissions, and organizational context.
- Establish clear AI boundaries
To maintain trust, we built around structured knowledge sources and clearly defined where AI reasoning should and should not be used.
The Architecture
WhitneyBot is built in three layers, each with one job, so the pieces can change independently.
Keeping these separate means the underlying language model can be swapped out, governance boundaries stay clear, and different roles get different answers without rewriting the logic each time.
Whitney Teams Agent — Component Architecture (v1)
- User message events
- OAuth SSO
- Adaptive Cards (future)
- Authentication (SSO via Azure AD)
- Token validation
- Message routing
- Conversation state storage
- Error handling
- Intent parsing
- Tool selection logic
- Multi-step orchestration
- Context memory
- Response synthesis
- Role-aware (Owner vs Member)
- Context-aware
- Skill-aware scaffolding
- Institutional workflows
- Naming conventions
- Indexed retrieval (RAG / search)
- Role lookup
- Teams & file metadata
- Permission-scoped access
- Secure token storage
- Logging & telemetry
- Hosting environment
- Future CI/CD
- Read-only operations
- No write access to Teams or Graph
- Governance-first rollout
Outcome
WhitneyBot is being developed as a Teams-native assistant designed to make institutional knowledge more accessible across the museum.
What I Learned
One of the most valuable product skills is diagnosing the right problem before building the solution.