Deal Intelligence

—— Scroll Down

Deal Intelligence

—— Scroll Down

Deal Intelligence

—— Scroll Down

—— Overview

Ridgemont Equity Partners needed to understand where AI could transform their business within Origination — fast. In 6 weeks, we went from zero to a working proof of concept, surfacing 32 AI opportunities, running a full discovery sprint, and delivering an intelligent inbox automation tool that changed how their origination team manages deals.

Client

Ridgemont Equity Partners

Date

January 6, 2026

Role

Sole Lead

Service

AI Strategy, UX Research, Rapid Prototyping

Contribution

Responsible for end-to-end AI strategy, stakeholder interviews, research synthesis, opportunity mapping, and working prototype delivered in a 6-week sprint.

—— Brief

From inbox chaos to intelligent deal flow: AI transformation for a private equity origination team

A 6-week discovery and rapid prototyping engagement that surfaced 32 AI opportunities, delivered a working proof of concept, and mapped a 12-month AI roadmap for a private equity firm's origination team.

43

AUTOMATION / AI OPPORTUNITIES IDENTIFIED

76

$76,000 AVERAGE SAVED IN ONE YEAR UTILIZING OUR SOLUTION

6

weeks from discovery to PoC

Note: The original deliverables from this engagement are confidential and cannot be shared publicly. The screens shown here are reconstructed mocks created to illustrate the product direction and design decisions, not reproductions of the final client work.

—— CHALLENGE

Private equity origination teams live and die by their ability to track, prioritize, and act on deals fast. But for Ridgemont's origination team, critical deal communications were getting buried in email, deadlines were being missed, and Salesforce wasn't being updated consistently. The result: missed opportunities and a team spending cognitive energy on administrative overhead instead of deal-making. Ridgemont engaged StealthX for a 6-week AI discovery and rapid prototyping sprint to understand where AI could have the highest impact and prove it with a working solution.

—— solution

The core insight from research: the primary stakeholder (Kelly, origination lead) never wanted to leave her inbox. Every tool or workflow that required context-switching was creating friction and non-compliance. The solution had to meet her where she already was.

01

Intelligent inbox automation

An AI layer built on Retool that monitors Kelly's inbox for deal communications, automatically creates or updates deals in Salesforce, and surfaces immediate action items back in her inbox — without her ever leaving her email client.

02

Smart deadline management

Automated deadline detection and reminder system that resurfaces time-sensitive deal actions at the right moment, reducing missed opportunities due to inbox overload.

03

Daily digest with conversational AI

A personalized daily email digest surfacing everything that needs attention or hasn't been acted on. Kelly can reply directly to the digest as a conversational AI interface which focuses on updating Salesforce, answering pipeline questions, or logging notes, all from her inbox.

—— 4 key design decisions

01 Leading with a daily digest instead of a dashboard
Early on we had to decide how to structure community within the app. The Facebook Group model was the obvious reference point, but it carries baggage. It feels public, performative, and algorithm-driven in ways that actively work against vulnerability. We landed on Circles. The distinction is intentional: a Circle is intimate, self-selected, and topic-anchored. Each has its own guidelines and keyword filters so members could navigate conversations around specific symptoms or treatment approaches without wading through noise. The name itself matters. A circle implies equal standing, no hierarchy, no algorithm deciding who gets heard.
02 Designing for trust in AI-generated output
Private equity analysts are trained skeptics. Presenting AI-synthesized intelligence to this audience without showing the reasoning behind it would have killed adoption immediately. A key design decision was building source transparency and confidence signaling directly into the output, so analysts could see not just what the AI was surfacing but where it came from and how to evaluate it. The interface needed to feel like a rigorous research assistant that kept logs, not a black box.
03 Keeping the prototype scrappy enough to be believable
In a 6-week sprint with a confidential client, there was real pressure to make the proof of concept look more finished than it was. We made a deliberate call to keep it grounded in real workflows and real data rather than polishing the UI at the expense of the underlying logic. A beautiful prototype that didn't hold up under a real analyst's scrutiny would have been worse than a rougher one that did. That judgment call shaped how we allocated time across the sprint.
04 Scoping the AI opportunity before designing anything
Before any design work began, the engagement was structured around a research-first spike to map where AI could create the most meaningful leverage across the firm's workflows. That sequencing was itself a design decision. It would have been faster to jump to solutions. Instead we ran stakeholder interviews and synthesis workshops to identify the highest-value opportunity before committing to a direction. The daily digest concept emerged from that process, not from a brief.

—— PROCESS

Weeks 1-2
Stakeholder discovery
Identified and interviewed all key stakeholders across the origination team. Synthesized findings to surface patterns, pain points, and unmet needs.
Weeks 2
AI vision workshop
Facilitated a full AI vision and value workshop with stakeholders to align on company goals, risk tolerance, and where AI felt most natural to the team.
Weeks 2-3
Opportunity mapping
Identified 43 distinct AI opportunities. Refined to top 10 through impact/effort scoring, then narrowed to top 3 for stakeholder presentation.
Weeks 5-6
Rapid prototyping & PoC
Designed and prototyped solutions around the chosen opportunity. Wrote requirements and handed off to development for a working Retool PoC.

The Override

The AI could have automated everything. But the insight that drove the design was deeply human: Kelly's relationship with her inbox wasn't a habit to break, it was a trust system. She knew where things were, how to find them, and how to act on them. Any solution that asked her to change that would fail regardless of how smart it was. The design decision to build the entire system that optimized her existing workflow, rather than replacing it, was what made adoption possible. That's a judgment call no model could make without understanding the person first.