Rizzy — AI Agent Operator Console

An AI lead-generation agent — the conversation UX and the operator-facing product around it.

Role: Product Design · UX/UI

AI lead-generation agents frequently run into complex edge cases or draft incorrect messages when parsing customer intent. Traditional platforms fail because they treat the AI as a direct customer-facing black box, giving human operators no way to inspect or correct messages before they are dispatched. Operators needed a command center that could monitor hundreds of active conversations, flag low-confidence steps, and enable instant human-in-the-loop overrides.

A split-panel interface with dual focus: a unified inbox of active conversations with priority scores, beside the agent's internal thought stream — retrieved context, model confidence, database citations. A confidence slider lets operators tune the threshold for auto-approval dynamically, and inline text editors allow instant message editing before sending.

Every AI-drafted reply lands in a status queue — New / Drafts / Rejected / Ready to send — so the operator reviews before anything ships.

Live thought-stream logging shows why a message is waiting, approved, or blocked.

Dynamic confidence bounds: higher-value conversations get stricter review without changing the whole workflow.

One persistent activity strip — tokens consumed, events per hour, intervention count — stays visible in every state.

Creating an agent is a chat, not a form. The agent asks focused questions — what to focus on, what it should never do — and every answer lands as structured configuration in a live side panel the operator can audit and edit. Do's and Don'ts are first-class rules, set before the agent ever sends a message. Right after setup, the operator runs the query manually and inspects the agent's output — insights grouped by source, every retrieved link — before switching it to automatic.

This case study is framed around the verifiable product work rather than growth metrics: a safer operator surface with approval queues, transparent logs, and inline correction patterns that make human review visible before AI-written messages leave the system.

Full case study → https://www.ssicevs.com/work/rizzy