Cover image for Exec Strategy Capital buys distressed

Exec Strategy Capital buys distressed and sub-performing commercial loans from community and regional banks. The landing page has one job: earn a credit officer's trust quickly and turn it into a loan tape submission. Design decisions: • The hero states the mandate in one line, with deal size, markets and time to close as facts you can scan in seconds. • Sections follow the order a lender asks questions: what you buy, how you work, who you are, how to send a tape. • A restrained palette of navy and slate with champagne gold as the only accent, Inter throughout, and a nested-hexagon motif that matches the mark. • One call to action, repeated in the nav, the hero and the footer. Fully responsive down to phone width. Role: design and build. Stack: Next.js, Tailwind CSS, Lucide icons.

2

1

53

Cover image for One system for a collections

One system for a collections agency's whole day: the accounts, the outreach, the payments and the paperwork. I designed and built it end to end. What I designed: • A visual workflow builder, a custom canvas built from scratch. Triggers, waits, branches, email, SMS, AI voice calls and collector tasks connect on one screen, so operations staff can change a follow-up sequence without a developer. • A manager dashboard: the monthly collection goal, cleared and post-dated payments, team performance, plans at risk and review queues. • A financial command center: a time-layered P&L from today through year to date. • An e-sign tracker with a verification view for every document: tamper check, event timeline, signing forensics and a public verification link. What runs behind it: 36 scheduled jobs handle the work nobody should do by hand, from sending campaigns and texts to warming up email domains, running payments and retrying declines, executing workflows every minute and keeping the AI dialer moving. Stack: Next.js 14, Supabase and Postgres, AWS SES, Retell, Vercel cron. All screenshots use demo data.

1

55

Cover image for Inbound payment calls look routine,

Inbound payment calls look routine, but every one carries risk: the caller has to be verified, a legal disclosure has to be read, and any offer has to follow policy. I designed and built an AI phone agent that handles the whole call, with a human one sentence away. What I designed: • A 30-node conversation flow: look up the caller by phone, confirm identity, read and log the required disclosure, then negotiate and take payment by keypad. • Guardrails that fire from any step. Attorney mentions, cease and desist requests, disputes and requests for a person each route to the right place and get logged. • A six-rung negotiation ladder: full balance, six payments, 80% settlement, 70% final offer, hardship plan, final probe. Plan math always sums to the balance, restated offers are paraphrased, one offer per turn. • Six agents that pass callers to each other during a call: English and Spanish inbound, declined-payment recovery in both languages, callbacks and identity verification. • An operator dashboard for live calls, outcomes, results by agent and compliance checks. How changes ship: every change is cloned into a sandbox, run through scripted test conversations that assert which exit fired, checked against named rules on the live flow, then published. Stack: Retell conversation flows, Python, Next.js, Supabase, Recharts. Dashboard screenshots use demo data.

1

40

EliteDial: AI voice platform built inside a collections agency

0

4

Dominic Sere

I build AI voice systems and the sales engine behind them.