Private AI governance workflow
Logo Proposal Validation Agent
I designed and shipped an internal logo-review workflow that moves clear cases in under one minute while keeping ambiguous decisions with reviewers.
Problem
What needed to change
Logo and brand proposal approvals were consuming reviewer time because submissions needed policy checks, judgment, drafted replies, and follow-up for unclear cases.
Users
Who the system serves
Brand reviewers, campus submitters, and marketing stakeholders.
Team context
Where I fit
Technical lead · AI product architecture · University of Arizona
I owned inception, architecture, development, publishing, documentation, and coordination with brand reviewers, marketing stakeholders, submitters, and development partners.
Important technical decision
Keep ambiguous decisions human
Combine deterministic policy checks with retrieved guidance and structured LLM output, then route unclear or sensitive cases to a reviewer.
Tradeoff or limitation
Where the boundary sits
Speed is valuable only for clear cases. Ambiguous requests stay human-in-the-loop rather than forcing an automated answer.
Implementation
What I personally owned
- Owned project inception, architecture, development, publishing, documentation, and stakeholder coordination.
- Designed the AI review flow from submission intake through approve, deny, ambiguous review request, and clarifying follow-up.
- Coordinated across development and stakeholder groups as interest grew beyond the original reviewer.
What the workflow exposed
The form was part of the problem
I found unclear fields in the request form, including a question people often answered strategically to move through it faster. That observation matters alongside the model: ambiguous and policy-sensitive submissions stay with human reviewers.
Result
Result and limitations
- AI review agent with approve, deny, ambiguous, and clarification paths.
- RAG and deterministic-policy checks with structured outputs.
- Channel notifications with approval and denial choices.
- Clarifying-question flow for ambiguous submissions.
- Tool calling to aid decisions as the system matured.
- Clear cases can move through the workflow in under one minute.
- Ambiguous and policy-sensitive submissions remain with human reviewers.
Technical scope