Work

Internal tool · 2025 · Slack + Claude API

Persona Focus Group

The hardest part of designing for a platform with five distinct user types isn't the complexity — it's the time. Getting quality, stakeholder-specific feedback meant scheduling five separate conversations and hoping the questions still held up by the time the answers arrived. I built a tool to collapse that lag to thirty seconds.

Role

Product Designer & Builder · End-to-end

Stack

Slack app · Claude API · Vercel

The problem

Five user types. Five opposing mental models.

VentureCrowd serves five fundamentally different user types. They don't just have different needs — they have directly opposing priorities. A feature that builds trust with a Retail Investor can actively undermine confidence with a Wholesale Investor. A UX decision that excites a Founder can be a dealbreaker for a Fund Manager. Getting honest, specific feedback from each group required scheduling that rarely happened before a direction was already committed to.

F

Founder

Raising capital

SL

Syndicate Lead

Running syndicates

FM

Fund Manager

Managing funds

WI

Wholesale Investor

Sophisticated capital

RI

Retail Investor

Individual investors

The solution

A panel discussion in Slack — on demand.

The bot runs in Slack — ask a question, get responses in a thread. Ask all five personas at once and watch where they split, or direct a question at one for a focused deep dive. Each persona is a carefully constructed system prompt: specific background, stated fears, a communication style, and hard limits on what they'll accept — grounded in real VentureCrowd archetypes, not generic investor stereotypes.

Thread· Persona Focus Group
A
Abbey Schott1:19 PM

Retail Investor: we're thinking of removing the minimum investment amount from deal cards so you only see it after you click through. does that change how you browse?

1 reply
Persona Focus GroupAPP1:19 PM

👤 Retail Investor

The minimum is one of the first things I check. Before I even read the company description properly, I'm doing a quick gut-check: is this even in my range? If it's $5,000 minimum I'm out immediately, and that's fine — I'd rather know that in 3 seconds than spend 10 minutes reading a pitch deck and then feel like I wasted my time. Hiding it until after the click feels a bit like those rental listings that don't show the price. You click through, you get invested in the story, and then you're either disappointed or you talk yourself into something you shouldn't. There's also a trust thing. When information feels deliberately withheld, I start wondering what else is being managed.

A single-persona deep dive in under thirty seconds. The response is specific, opinionated, and grounded in how this user type actually thinks — not a generic UX principle about information hierarchy.

Example output

The value is in the tension.

The most useful outputs aren't the ones where everyone agrees. A question about showing the full cap table on every deal page produced directly opposing answers from the Founder and the Retail Investor. Neither answer alone would have shaped a useful design direction. The conflict between them did.

Persona Focus…
Home
Messages
About
#general
#product-research
#design
A
Abbey Schott
# product-research
A
Abbey Schott1:21 PM

ask the Founder and Retail Investor: we're thinking of showing the full cap table, including all existing investors and their ownership percentages, on every deal page before you invest. good idea?

8 repliesLast reply today
Thread· Persona Focus Group
A
Abbey Schott1:21 PM

ask the Founder and Retail Investor: we're thinking of showing the full cap table, including all existing investors and their ownership percentages, on every deal page before you invest. good idea?

8 replies
Persona Focus GroupAPP1:21 PM

🏢 Founder

Hard no from me. My lead VC has a standard clause about not publicly disclosing the cap table, and I'm fairly sure most serious angels expect the same. The moment that information is publicly visible — before someone has even signed an NDA — I've got a problem I have to explain to my existing investors. That conversation costs me goodwill I can't afford mid-raise. There's also a competitive angle. We're in climate tech, a space where a few well-funded players are watching what we're doing. Showing them exactly who's backing us and at what dilution, before we're closed, is not something I'd sign off on.

Persona Focus GroupAPP1:21 PM

👤 Retail Investor

Honestly sounds really good to me, and I'm a bit surprised more platforms don't do it already. When I look at a deal, one of the first things I want to know is who else is in this — not in a 'following the crowd' way, but more: is there a credible lead investor who's done proper due diligence? Are there any weird red flags, like one person owning 90% and selling down? Seeing the cap table would help me ask those questions myself instead of just hoping the deal page summary is telling me the whole story.

Founder

Hard no from me.

The moment that information is publicly visible, I've got a problem I have to explain to my existing investors.

VC NDAs + competitive exposure = dealbreaker. Wants tiered visibility — verified wholesale investors only, post-NDA.

Retail Investor

I'm surprised more platforms don't do it.

Is there a credible lead investor who's done proper due diligence? Seeing the cap table helps me ask those questions myself.

Wants the credibility signal. Cap table visibility is how they assess deal quality — it's information, not complexity.

Same question · Opposite answers · Both valid

This thread didn't produce an answer — it produced a design brief. The right solution isn't full public disclosure or full opacity; it's a tiered visibility model that gives each persona what they actually need.

What this enables

Research happens before the commit, not after.

The practical value isn't just speed, though thirty-second research sessions instead of five scheduled interviews is genuinely useful. The deeper shift is that it changes when research happens. Because the cost of a gut-check is zero, I can pressure-test a product idea before investing any design time — not after a direction has already been handed to a developer. Copywriting decisions, feature scope, onboarding flows, pricing framing — things that would previously run on instinct now have a fast feedback loop.

Built end-to-end

The engineering is the scaffold. The value is in the prompts.

I built the bot end-to-end — Slack app wiring, Claude API integration, deployed on Vercel. The persona prompts were written and refined by me, drawing on direct knowledge of VentureCrowd's user base built over four-plus years. Each prompt includes a specific background, first-person voice, stated fears, and constraints that generate realistic tension between responses.

Slack AppClaude APIVercel