AI Query Risk Check
A Voiceflow prototype for workplace AI governance triage
designed by Kirsten Johnsen for a ConnexAI application.
A Voiceflow prototype for workplace AI governance triage
designed by Kirsten Johnsen for a ConnexAI application.
I build practical systems that help people use technology with more confidence, clarity, and care.
I turn complex workflows into usable processes that support both the people doing the work and the organization they serve.
I am especially interested in the space where conversation design, operational workflows, customer support, and responsible AI meet. I believe the best systems are not just technically functional; they help users make better decisions in the moment.
AI Query Risk Check is a lightweight chatbot prototype that helps workplace users determine through whether a planned AI query is likely low risk, needs revision, or should be reviewed before use.
The demo version was built in approximately 2.5 hours. It uses a structured Voiceflow intake workflow followed by an LLM-assisted prompt risk interview to give users practical, plain-language guidance.
More employees are using AI tools in daily work, and organizations need simple ways to help people pause before sharing sensitive, confidential, regulated, or decision-related information. However, many organizations are not creating or using clear AI governance policies and employees are turning to using personal accounts with corporate information.
This bot is not designed to approve AI use or replace internal policy. It is an informational triage assistant that helps users identify risk signals, consider safer prompt approaches, and decide whether a planned query should be revised or not used.
The prototype uses a hybrid design. A deterministic intake workflow collects consistent variables such as policy status, organization type, query purpose, data type, and output use. That workflow sets a minimum risk level before the user enters the more flexible prompt interview.
The Prompt Risk Interview playbook then asks for a high-level description of the planned AI task. The LLM can raise the risk level based on the user’s description, but it cannot lower the minimum risk set by the workflow. This keeps the governance-critical logic predictable while still allowing natural conversation.
GPT-5 nano is used because the level of complexity in this query, when combined with the structured text from the deterministic intake does not require a LLM that can process large amounts of data.
This demo provides general risk-awareness guidance only. Please do not enter real sensitive, confidential, regulated, personal, customer, student, employee, financial, health, HR, legal, proprietary, or security-related information.
The chat widget launches from the lower-right corner of the page. Use the button above if the widget is minimized.