Private AI guidance tool

Brand Guidance Chatbot

A tested chatbot concept for answering brand and policy questions, making guidance easier to find, and reducing repeated stakeholder support load.

Internal Systems Prototype 2024 - Present

Role

AI Tooling Tester / Builder

University of Arizona

Tags

AI GuidanceRetrieval ConceptsStakeholder Support

Problem

Campus marketers needed faster access to brand guidance so they could answer policy and copy questions without manually searching the MarCom site or asking the same support questions repeatedly.

Users

University marketers, campus communicators, and internal teams responsible for brand-aligned messaging.

Ownership

  • Owned the project from inception to prototype.
  • Led user testing because the tool was intended for campus-wide use.
  • Designed the prototype as part of a broader brand-governance and stakeholder support ecosystem.

Hard Parts

  • Designing an update process so the chatbot could rebuild when the source site changed.
  • Adding safeguards so the bot would not collect sensitive information or answer questions it should not answer.
  • Balancing helpful guidance with trust, boundaries, and policy-sensitive escalation.

Leadership

  • Led the prototype and user testing process.
  • Made security and safe-use constraints part of the workflow rather than an afterthought.
  • Connected the chatbot to broader AI-assisted brand governance work.

Shipped

  • Working prototype for brand and policy guidance.
  • Source update/rebuild process concept.
  • Guardrails for sensitive information and out-of-scope answers.
  • Internal testing workflow with team members and campus users.

Impact

  • Already used internally by team members as an alternative to browsing the MarCom site for information.
  • Currently in user testing to validate broader campus usefulness.
  • Creates a foundation for scalable, governed brand guidance.

Highlights

  • Explored brand and policy question-answering to make guidance more discoverable for campus users.
  • Connected the concept to the larger AI-assisted brand governance and stakeholder enablement ecosystem.
  • Focused on reducing repeated support load while preserving clarity around policy-sensitive answers.
  • Used the prototype to evaluate where conversational guidance could fit into existing review workflows.

Tools

LLM workflowsBrand/policy guidanceRetrieval conceptsChatbot testingStakeholder supportContent governance