Prospect Mining

Prospect Mining
Arcadea Group/Prospect Mining
Case study · 2025 · Arcadea Group · Generative-AI product

An investment-development co-pilot that shows its work.

Designing the interface for Prospect Mining — a generative-AI tool that helps Arcadea's investing team find, understand, and reach acquisition targets, and lets a non-technical Managing Director correct the model in ten seconds when it's wrong.

🔒  Arcadea AI
Prospect Mining company profile — a persistent left rail with filters and a dark deal-details panel, beside a tabbed Overview showing an AI-written company summary.
The Company Profile. A persistent identity rail and deal-stage panel on the left; four AI lenses on the right — Overview, Arcadea GPT, Full Contact Listing, and Ground Truth.
My role
UI / UX design
Client
Arcadea Group
Year
2025
Domain
Investment development · Software M&A
Platform
Streamlit web app on Azure
Built with
Arcadea AI Team — ML & backend

01 · The brief

Finding a needle, by hand, in a haystack of thousands.

Arcadea acquires vertical-market software companies. Its investing team spends enormous effort researching thousands of candidates to judge one thing — is this a genuine VSaaS acquisition target? — and then reaching the right people. That work was manual, slow, and hard to keep consistent.

The Arcadea AI Team's answer was a co-pilot, not an autopilot: a tool built on Azure Cognitive Services that does the routine gathering, scoring, and drafting, then hands the judgement back to a person. My job was the interface — the part the Managing Directors actually touch. It's also where my engineering past pays rent: designing for a probabilistic system means understanding what the model can and can't know.

And building the correction flow for when it's wrong. That framing set the whole design problem. A probabilistic system making high-stakes calls is only used if the experts on the other side can see its reasoning, trust the parts worth trusting, and overrule the rest without friction. The screen had to earn that trust.

Core task 01

Score the target

Predict how likely a company is to be an acquisition fit — surfaced as a plain-language probability, with the reasoning one click away.

Core task 02

Draft the outreach

Combine existing email templates with more nuanced, per-company messaging — drafted for review, never sent blind.

Core task 03

Centralise everything

Keep every learning inside one tool through two-way integrations with Salesforce, SalesLoft, and LinkedIn.

A powerful tool — yet it'll only be as effective as its human counterpart. — Arcadea AI Team, internal launch note

02 · Scope & constraints

What I owned, and what fought back.

I designed the product interface end to end — the information architecture, the screen layouts, the tab system, the data-state language, and the human-in-the-loop correction flows. The AI models, pipeline, and integrations were the Arcadea AI Team's.

  • Streamlit as the canvas. A data-app framework, not a design tool — I worked within its component set to make something that still felt considered.
  • Dense, expert content. Four ML models, summaries, contacts, and deal signals all converge on one company view without overwhelming it.
  • A skeptical, busy audience. Managing Directors, not analysts — every screen had to reward a ten-second skim and a five-minute deep read equally.
  • Trust in a probabilistic system. The hardest constraint wasn't visual. It was doubt: the design had to make the model both legible and correctable.
03 · How it works

Thirteen automated steps — and two moments that belong to a human.

The pipeline mirrors the research the team used to do by hand. Mapping it revealed the real design insight: the interface only has to be excellent at the two decision points where a person steps in. Everything else runs quietly underneath.

GatherSteps 1–4
Pull companies from Salesforce Store in Cosmos DB Gather data features Scrape company website Store features
DetectSteps 5–6
AI / ML detection of VSaaS Store results Is it VSaaS?
GenerateSteps 7–9
Gather LinkedIn data Generate initial email Store email Queue in SalesLoft for review
ReviewSteps 10–11
Is this email appropriate? Send email
LearnSteps 12–13
Query SalesLoft for responses Retrieve feedback from tool Store for future use
Automated step Stored / learned Human decision point
04 · The interface

One screen that answers “who am I looking at?” before you ask.

The Company Profile is the home of the tool. I split it into a fixed identity rail and a working area of four tabs, so context never leaves the screen while you move between lenses.

🔒  Arcadea AI  ·  Overview
The Overview tab for a healthcare-imaging prospect: filters and the deal-details panel on the left, an AI-written company overview with predicted industry and key phrase on the right.
The Overview tab. Left rail: VSaaS status, industry and company filters, then the dark deal-details panel. Right: the AI-written summary, predicted industry, and a generated key phrase.
Company Details
HighVSaaS probability
0# Emails sent to prospect
0# Email responses
0# Bounced emails
NoSubstantial contact
NoNDA signed
NoLOI issued
NoIOI issued
NoClosed
Design decision · a colour language for state

The deal ladder reads at a glance.

Every company carries the same panel, so an MD builds muscle memory. I gave the data a consistent colour grammar rather than leaving raw text: emerald for a strong signal or a clean “no” early in the funnel, amber for the counts that measure momentum. The probability sits at the very top, in words — High, not 0.9134 — because a person is meant to judge it, not decode it.


05 · Making the model legible

Skim first. Drill only where you're curious.

The Overview leads with a plain summary, then folds the evidence into expandable sections. An MD reads two paragraphs and moves on — or opens the drawers and interrogates every claim.

Overview · expandable evidence
The Overview tab showing the AI summary followed by collapsed drawers: LinkedIn Summary, Product Summary, Product List, and Industry Summary.
Progressive disclosure. Six drawers — LinkedIn, Product Summary, Product List, Industry, B2B Analysis, and the VSaaS rationale — sit collapsed beneath the summary.
Two lenses, one page

Evidence on demand

  • The key phrase and predicted industry lead, so the model's headline claim is visible instantly.
  • The VSaaS Identification Analysis drawer explains why the tool scored the company the way it did — reasoning, not just a verdict.
  • Arcadea GPT is a second tab: a chat, with five ready-made prompts to give MDs a running start and a free-text box for anything else.
06 · The trust layer

Ground Truth turns every skeptical expert into a teacher.

This is the heart of the tool. Four models predict a company's category, industry, key phrase, and outreach angle. When one is wrong, the MD doesn't file a bug — they fix it inline, and the correction becomes training data.

Correction as a ten-second aside

Designed so fixing it is easier than ignoring it

  • A star rating asks one honest question first: how accurate is this listing overall?
  • Each wrong field has its own gentle prompt — “Industry incorrect? Fix it here” — with the right control already in place.
  • A free-text box captures the why when a dropdown can't, so the model learns nuance, not just labels.
  • Nothing feels like punishment. The tone is a request for help, because a corrected model is the whole point.
Arcadea AI · Ground Truth
The Ground Truth tab: an overall accuracy star rating, then per-field correction controls for industry, designation, and key phrase, with free-text boxes for explaining what was wrong.
The Ground Truth tab. Rate the listing, correct any field in place, and explain the miss — feeding the four models directly.
The design brief was really doubt — and the answer was to make correcting the AI feel like a favour, not a chore.
07 · The connective tissue

A co-pilot that lives inside the tools the team already uses.

Prospect Mining doesn't replace the stack — it plugs into it. Salesforce stays the source of truth; SalesLoft runs the outreach. My design work here was the seam: showing what flows where, so nothing feels like a black box.

Salesforce · synced fields
A Salesforce account record showing two fields written back by the tool: a VMS Score and a PM Description generated by Prospect Mining.
Two-way Salesforce sync. The tool pulls the company list to begin its work, then writes a VMS Score and PM Description back to the CRM.
Salesforce & SalesLoft

Automation you can audit

  • Salesforce remains the core CRM. Prospect Mining reads from it to start, and pushes scoring and summaries back — a genuine round trip.
  • SalesLoft receives the AI-drafted cadences. Each day the MD reviews the queue, sends what's right, and polishes what isn't.
  • Sent, read, and reply rates flow back in — closing the loop so the drafting gets sharper over time.

Salesforce and SalesLoft are third-party products Prospect Mining integrates with; those screens are the integration surface, not my UI design.


08 · Design language

A quiet palette, so the data can speak.

Arcadea's own identity is spare — a black wordmark on white. I kept the product in that register and spent all the colour on meaning: state, signal, and the human touch.

Slate
#2A2D3D
The deal-details panel; anchors identity
Bone
#F4F2EC
Calm working ground
Signal
#DB4A3E
Active tab · the human moment
Emerald
#2F7A57
Positive state · strong signal
Amber
#BF8829
Counts · momentum metrics

Type does the hierarchy. A characterful serif for company names and section heads, a readable serif for the dense AI summaries, and a monospace for data, labels, and the deal ladder — so numbers and states always look like facts, distinct from prose.

Structure repeats on purpose. The same rail, the same four tabs, the same colour grammar on every company. Consistency is what lets an expert stop learning the tool and start using it — the highest compliment a working interface can earn.

09 · Reflection

Designing for a machine that's often, but not always, right.

01

Legibility beats accuracy

A 91% model an expert can't inspect gets ignored. Showing the reasoning — the VSaaS rationale, the source drawers — mattered more to adoption than the last points of precision.

02

Correction is a feature, not an error path

Ground Truth treats being wrong as ordinary and fixable. Framing correction as helping — not reporting a fault — is what turns a tool into a system that gets smarter.

03

Meet experts where they work

Living inside Salesforce and SalesLoft, in plain language and a familiar layout, did more for trust than any amount of visual polish could have.

End of case study
Ishanka Munasinghe

Prospect Mining — the UI/UX for Arcadea Group's generative-AI investment-development co-pilot: interface design, a data-state colour language, and the human-in-the-loop correction flows.

UI · UX · Product
Arcadea Group · 2025
Set in Fraunces, Newsreader & IBM Plex Mono Palette: slate #2A2D3D · signal #DB4A3E · emerald #2F7A57 · bone #F4F2EC

Built with the Arcadea AI Team (ML & backend) on Azure Cognitive Services, Cosmos DB & Streamlit. The application sits behind Arcadea single sign-on; screens shown are from the internal product deck & user guide.