top of page

Ask Rivi

Frame 9.png

Ask Rivi is a contextual AI assistant embedded within the recruiter workflow. It helps recruiters source and evaluate candidates, enabling them to take the right actions faster with confidence. ​

​​

As a sole UX designer, I uncovered where recruiters need AI tool the most and designed the experience from the ground up, shifting Ask Rivi from a passive content generator to an active decision-support layer. Within a month of beta launch, 70% of controlled users were actively using the feature in their workflow. 

The Problem:
Expanding AI Without a Strategy

Sutro’s AI writing assistant (below) launched as a standalone feature, and users liked it. Leadership wanted to build on that momentum quickly, with three separate AI tools for three tasks: Chat, Docs, and Recruiting.

The intent was valid, but the plan had UX and delivery risks. Recruiters do not need more AI tools. They need AI that understands their context and workflow.
 

  • Three tools, three mental models: different names, entry points, and behaviors. Users have to decide which tool to open before they get any help, and inconsistent behavior erodes trust in the output.

  • Repeating an existing mistake: the product already had duplicated features, and users were already complaining about them.

  • Not enough capacity to do it all: with a lean engineering team, building three complete tools meant either waiting months for everything, or shipping partial tools that disappoint users early.

Screenshot 2026-02-19 at 6.47.17 AM.png

UX Strategy:
From 3 Tools to 1 Sourcing Engine

To address the fragmentation risk, my goal was to design a workflow-aware AI assistant as the global AI delivery model for the MVP, a cohesive AI experience that functions as a contextual task assistant rather than a collection of isolated LLM features.

​

I then pulled evidence from three places to pitch to leadership: competitive research on how other platforms deliver AI, the duplicated features in our own product that users were already complaining about, and concept testing with 5 recruiters which validated issues with fragmented experience.

​

My proposal for the MVP was to focus on sourcing, the stage where users need AI most, while the current writing assistant stays as is for now. The north star is to expand this across the recruiting pipeline into one unified experience. Leadership agreed, and I moved on to defining the detailed scope.

Journey.png

Through shadowing sessions and structured interviews with target users, I mapped the full recruiter workflow from job setup to offer. Sourcing stood out as the most manual, most time-intensive stage and the clearest opportunity for AI to deliver immediate value.

Screenshot 2026-02-19 at 6.47.43 AM.png

To move beyond ad-hoc AI features, I developed the AI Delivery Types framework - Global, Inline, and Passive models with specific AI capabilities tiled user mental models and workflow patterns.

While the North Star vision encompasses all three, we prioritized the Global delivery type for the MVP as the foundation of a unified AI experience with a consistent "command center" for AI interactions.

Body.png

I designed the end-to-end AI workflow to shape the experience holistically from discovery and prompt input to processing, review, and iterative refinement. Rather than focusing on a single UI surface, this framework defines how AI behaves across each stage throughout the workflow.

Agentic states.png

As an AX designer, I go one layer deeper than UI, mapping how the agent thinks, decides, and recovers before a single screen is designed. This diagram shows the agentic system states for the Ask Rivi sourcing workflow, from idle through failure recovery and completion. Each state defines how the agent operates at that moment: what it needs to function, where it can break, and what the system must handle before anything surfaces to the user.

 

The color tags connect each state back to the AI workflow pattern above, making the relationship between system logic and human-facing experience explicit. Understanding what happens under the hood is how you ensure the AI behaves reliably, and how that reliability shapes an experience users can trust.​

Design Framework:
Contextual Sourcing Assistant

Rather than designing individual mockups for every AI interaction across Sutro, I built a reusable interaction model using sourcing as the primary use case (from UX strategy). The goal was to define how Ask Rivi thinks, responds, and behaves through one well-documented workflow, and hand that off to engineering as a blueprint they could apply consistently with the repeatable pattern and logics.

Screenshot 2026-03-09 at 12.48.56 AM.png
Brand Identity

I designed a distinct iconography for Ask Rivi to establish a unique AI identity within Sutro. The system scales from logo to action and status icons while remaining clear across sizes and color themes. The screenshot above details the design rationale and decision-making behind the iconography proposal.

Frame 1.png
Discover

​Recruiters can easily launch Ask Rivi from the global header once they’re ready to source, making the assistant visible and accessible without disrupting the existing Sutro job flow. This entry point supports faster candidate discovery by introducing AI at the moment of need while keeping the experience non-intrusive.

Frame 2.png
Initial Launch​

When recruiters launch Ask Rivi, the assistant recognizes the active job and current workflow state, guiding users toward the most relevant next steps in context.

 

Rather than open-ended prompts, the interface surfaces up to three guided quick actions ordered from soft to assertive, starting with exploratory suggestions like "show me recommended filters" before progressing to more committed actions like "apply filters and find candidates." This progressive trust model lets users ease into AI-assisted decisions at their own pace before they fully commit to relying on result driven by AI.

Frame 4.png
Input / Processing​

AI latency is where user trust often breaks. To prevent the "did it work?" moment of doubt, I designed staged processing updates that surface in real time. By showing exactly what Rivi is retrieving, analyzing, and generating, the interface provides immediate feedback. This transparency reassures recruiters that their request is progressing, keeping them engaged instead of second-guessing the system.

Frame 6.png
Output / Review

Ask Rivi returns recommended filters with inline reasoning, citing the specific sources it used, styled as reference chips that open a document preview in a modal for instant verification without leaving the workflow.

 

Recruiters can also copy the output or leave direct feedback via thumbs up/down, feeding signal back into the system over time. The structured format is easy to scan, and actions follow the same progressive model: lighter confirmations first, stronger executions after.

Frame 7.png
Refine / Processing (Loop)

When a recruiter commits to an action, the interface enters a synchronized loading state to ensure a clean handoff between the user and the AI. Ask Rivi provides real-time status updates in the side panel while the main sourcing UI temporarily disables interactions, such as filters and buttons.

​

This interaction model prevents mid-execution conflicts and clearly signals that the system is processing. Once Rivi completes its analysis, control is handed back to the recruiter with results ready for review, making the transition from AI-processing to human-evaluation clear and deliberate.

Frame 9.png
Refine / Iterate

Once Ask Rivi completes its evaluation, control returns to the recruiter with a clear summary, breaking down matches into Strong, Medium, and Low tiers based on the applied filters and job criteria. The main UI updates simultaneously with ranked candidates and match strength indicators so recruiters can scan and act immediately.

 

Ask Rivi triggers actions and surfaces insights, but Sutro's main UI is where recruiters review, evaluate, and make final decisions. This separation ensures that the AI assistant remains a streamlined tool for workflow acceleration, while the Sutro platform remains the primary "source of truth" for deep exploration. 

Frame 10.png
AI Informed - Humans Decides

Clicking a candidate card expands an inline detail view showing a Rivi Score, key highlights (experience, industry, location), and 3 to 4 fit signals grounded in job requirements and alignment documents. Two actions close the loop: "View Full Profile" opens the full candidate record in a new tab, while "Move to Pipeline" advances the candidate without breaking the sourcing flow.

​

Ask Rivi initiates, Sutro decides. Every design decision in this framework was made to keep the users in control while letting AI do the heavy lifting.

The Outcome:
MVP Release and What Came Next

This was an intense 0 to1 product built quickly with a lean engineering team. The MVP release produced:

  • Achieved 70%+ adoption within the first month, with positive user feedback through thumbs-up ratings.

  • Contributed to a 11.7% reduction in average search duration, accelerating candidate placement.

  • Helped increase monthly placements with 8%+ uplift in hiring throughput.

 

It wasn't just moving users efficiently throughout the workflow. It was also a  great way set the foundation for a unified AI experience, establishing a blueprint for continued growth and iteration.

Frame 8.png
bottom of page