Fotios Mpouris — Builder, Operator

“The builder’s hat must be on; this is the era for everybody to try to build, try to think, and try to dream of what’s possible.”
— David Friedberg

Poor People App I’ve always heard that if you’re going to build an app, build something that solves a problem you’re having or that isn’t solved yet. The Poor People App is helping me care for my aging parents, and it’s just one of the many problems we’re solving.

Hard-E Hard-E is a digital employee. Connected to a company CRM, it can email, text, and learn. Special knowledge files, the ability to synthesize material costs, provide measurement and pricing data. Available hands-free in voice mode.

All Angles One of the most interactive websites we’re building is for an exterior remodeling company — aiming as close to future-proof as we can. Integrating interactive and educational forms, vision models to interpret customer photos of their homes, digesting and presenting intelligence for sales agents, and building AI agents with capabilities that allow for true digital–human collaboration.

Ethos Ethos is my first autonomous agent — built on Hermes. It coordinates care for my parents through a live OpenCare API, runs a video intelligence pipeline that turns YouTube into wiki-linked investment signals and more. Employee, volunteer, partner.

Serving Defense, Healthcare, Social Services & Government

The Poor People App is being built around a principle of investment and community — things that are clearly missing, or being diminished at a rate that makes us all take a step back. Everyone has a family. Our goal is to help your families get care, navigate current technology, and coordinate community-based support using the same frontier technology that’s changing the world as we speak.

We also want the people who show up to provide that help to have experience — so we’re integrating retired military, law enforcement, fire, and EMS to lead the most important part of our mission: the safety of our users. The Sentinel Program is the trust infrastructure: retired professionals full of hard-won experience, eager to help their community, and finally, with the advent of our new coordination tools, in a position to do it at scale.

Veterans · Military Families · First Responders · Nonprofits · Caregivers · Underserved Communities — Reach Out

Poor People App — A Brief

More Information on Core Builds

LIVE

Poor People App / OpenCare — When you have a problem, build a solution

I was drowning in group texts trying to coordinate my parents' care: doctors, insurance renewals, medications, siblings who needed updates but didn't need another app. So I built OpenCare: a care coordination platform where circles of helpers organize around the people who matter, with tasks, reminders, and daily digests that reach even the family members who barely check email.

Then the mission grew. OpenRecovery applies the same circle model to substance use and dual diagnosis recovery — 10 modalities, daily check-ins, adding supportive members, and Recover E, an AI voice companion that’s sharp, challenging, and built for people who want to do the work.

These two apps live under the Poor People App umbrella — a platform for the rest of us, where the goal is to have AI manage the coordination layer that most professionals must charge extra for because of their administrative overhead. We want our technology to handle the 95% of bureaucratic work that’s purely procedural. We want human Sentinels to handle safety and real judgment. AI is not ready to make decisions for us, but it can definitely help us coordinate and help us make better ones.

53M unpaid US family caregivers · 19M US veterans · The skills to help are already in our communities — we’re building the infrastructure to activate them.

opencare.poorpeople.app · poorpeople.app · Learn More →

PRODUCTION

Hard-E — AI Sales Director for Contractors

Hard-E is a full production agent for home service contractors. It connects directly to a CRM with 21 tools that cover the entire sales workflow: customer lookup, job management, pipeline stage updates, SMS, email, appointment scheduling, proposals, financials, pricing, and document handling. Some of those CRM endpoints don’t even exist in the official API — they were reverse-engineered from browser dev tools to get features like email access and note notifications working.

The voice mode is what sets it apart. Deepgram transcribes speech, Claude Sonnet 4 reasons and picks which tools to call, and Cartesia speaks the response back — all in real time over WebRTC. A user can ask Hard-E to check on a customer’s job status mid-conversation and get the answer without the call breaking stride. The entire voice pipeline runs as a separate Pipecat process alongside the main API.

It remembers. A background service watches for idle sessions, extracts what was learned — customer preferences, pricing patterns, workflow corrections — and stores it. Next conversation, that knowledge is already in context. Voice sessions get the same treatment: when a call ends, the system summarizes and saves anything worth keeping.

Multi-tenant, encrypted credentials, tenant-isolated knowledge bases, invite-based trials. Built to clone — swap the CRM plugin, rewrite the personality file, upload new training documents, and it becomes a sales director for a different industry. We’ve already started doing that.

FastAPI · React · Redis · S3 · Claude Sonnet 4 · Pipecat · Deepgram · Cartesia · EC2

harde.app

TECHNICAL LEAD

All Angles — Remodeling How Remodeling Gets Sold

Most contractor websites are brochures with a contact form bolted on. This one had to be different — the founder spent 30 years watching the industry get it wrong. Hard sells, vague estimates, leads that go nowhere. All Angles launched as a startup built on the opposite: educate first, earn trust, then ask permission.

So I built the entire conversion around that. No contact form. Instead, a guided interactive journey that walks homeowners through the process at their own pace. By the time they reach the end, they've learned something, they've uploaded photos of their home, and they've decided on their own terms that they're ready. That's when the system asks for one thing: permission to come measure.

Supabase backs the data layer and analytics. Uploaded photos process through GPT-4o Vision, which reads the exterior — siding material, trim condition, visible damage. Perplexity researches the property. The contractor receives an AI-briefed dossier on a lead who already said yes, before he’s picked up the phone. Hard-E is also integrated into the business’s operational layer, handling both consumer-facing and internal CRM workflows — a working example of what it means to employ a digital worker across an entire operation.

Next.js 14 · Supabase · GPT-4o Vision · Perplexity · AWS (SES, S3, DynamoDB) · James Hardie Elite Preferred

aaexterior.com

ALWAYS ON

Ethos — Personal AI, Running Continuously

Ethos runs 24/7 on AWS Lightsail — voice and text over Telegram. It coordinates care tasks via the OpenCare API, processes video research through a multi-lens pipeline, and maintains a living knowledge base across investing, technology, and frontier science. Over 100 pages, growing weekly. It delegates to cheaper models when it can, resets its own sessions, and curates its own skills. We continually research open-source builds, integrate the best developments, and apply a creative perspective to advance what Ethos can do — because the most interesting version of this is always one iteration away.

$2–4/day · 100+ wiki pages · Hermes Agent · Voice-enabled

Internal system

How I Got Here

I came into this sideways. I built and ran The Grillin Greek for over a decade — operations, customers, staff, systems, and a passion for community leadership and engagement. I learned what actually matters, and how important it is to stay healthy, and the hard lessons you endure when you don’t put your family and your belief in God first. From there it was art, then graphic design, then Unity game development and Python. By then the LLMs had arrived and everything accelerated.

The agents handle what agents handle well. I handle what still requires a human: the judgment calls, the vision, the question of whether a thing should exist at all.

The pattern holds whether you're coordinating elder care or field operations, running financial compliance or clinical intake, navigating a nonprofit's grant cycle or a contractor's job pipeline. The domain changes. The infrastructure doesn't.