AI Knowledge Assistant Prototype • 2026

AJC AI Knowledge Navigator

A staff-facing prototype designed to make workforce-program information easier to navigate through conversational questions, focused follow-ups, program routing and source-aware guidance.

Current state

Working prototype for demonstration and staff testing. It is not presented as a production case-management, eligibility or automated decision system.

Representative AJC AI Knowledge Navigator interface
Representative portfolio visualization based on the reviewed prototype and verified V3.8 behavior.

The problem

Workforce-program questions often begin with incomplete information and may require staff to move between program rules, agency resources, forms and referral sources. I wanted to explore whether a conversational interface could help staff reach the relevant program or source more efficiently while still asking for clarification when missing facts could change the answer.

What I designed into the workflow

CONVERSATION
Focused follow-up questions

The assistant can ask up to three clarifying questions when the answers could materially change the outcome.

ROUTING
Program-aware guidance

Regression coverage includes OSY/YESS, SNAP, Ticket to Work and Dislocated Worker routing.

AGENCIES
Source-aware direction

The workflow distinguishes AJC programs from external responsibilities such as Nebraska DHHS and SSA.

FORMS
PDF form-pack safeguards

Testing checks that the form-pack workflow stays within the intended PDF-only rules.

CONTEXT
Conversation continuity

Previous follow-up questions remain in history so short replies can still be interpreted in context.

NAVIGATION
Simple return-to-home behavior

The AJC logo is tested to return users to the Navigator home state.

Representative tested scenarios

The images below recreate representative test interactions aligned to behaviors documented in the V3.8 regression record. They are not production-user screenshots.

Representative AJC AI Knowledge Navigator routing tests
Documented routing coverage includes Dislocated Worker, SNAP → Nebraska DHHS, Ticket to Work → SSA and OSY/YESS.
Representative AJC AI Knowledge Navigator follow-up question flow
Follow-up behavior is capped at three questions and preserves conversational context.

Testing discipline

The V3.8 test record documents successful checks for the structured follow-up schema, follow-up limits, prevention of unnecessary or repeated questions, PII-aware clarification rules, conversation-history preservation and existing answer/form-routing behavior. Regression checks also cover OSY/YESS, SNAP → Nebraska DHHS, Ticket to Work → SSA, Dislocated Worker layoff routing, PDF-only form-pack safeguards and AJC-logo navigation.

3 max

follow-up questions per assistant turn

4

named program-routing scenarios represented in the regression record

PASS

PDF-only form-pack safeguard regression check

PASS

follow-up history and clarification UI checks

What this project demonstrates

The project goes beyond building a chatbot interface. It demonstrates requirements definition, iterative AI-assisted development, workforce-program routing logic, conversation design, UX refinement, safeguards and regression testing — translating a complicated staff knowledge problem into a testable prototype.

Scope

The Knowledge Navigator is a prototype intended for demonstration and staff testing. I am not presenting it as an approved production system or as evidence of measured staff or participant outcomes.