AI Systems in Production · Los Angeles

Built. Shipped. Running.

The models are built. The last mile isn't. I install AI into businesses that run on trucks, permits, and phone calls.

Everything on this page runs in production — agents doing real work with real money and real customers, not demos. I'm an operator, not a vendor: twenty years of P&L ownership, and today I design, code, and self-host AI systems end to end. Most of it I architected and shipped myself; two products are built by developers under my direction.

Nine systems, one operating principle

AI does the persistence and the volume; humans approve what matters; everything is logged.

Internal AI operating system

Self-hosted · replaced Basecamp as our project manager

A Markdown-native workspace with Git as the source of truth, an in-browser editor with an AI coding agent pre-installed for every teammate, and a live operations dashboard — all behind a single MCP gateway (one Cloudflare Worker handling sign-in and SSO, routing internal AI tools like memory, SEO, PPC, and analytics, and audit-logging every tool call for cost attribution). The team works inside it daily.

I redesigned project management itself around AI hand-offs — and replaced our SaaS PM tool with what I built.

Hunter — autonomous PPC agent

Google Ads + Microsoft Ads · human-in-the-loop

An always-on agent that builds campaigns, monitors performance, defends against the platforms' auto-applied changes, and proposes fixes with one-tap approval over Telegram. CRM-grounded, governed by explicit written rules, every action logged.

Replaces the day-to-day work of a PPC manager — with a human approval gate on every change.
kpicreatives.com/hunter

Oscar — YouTube ops agent

Self-hosted analytics + channel management

A self-hosted agent exposing dozens of tools across analytics, discovery/SEO, channel management, captions, and bulk reporting — multi-channel, queryable in plain language through an AI client.

Replaces a stack of dashboards and manual reporting with one agent you can just ask.
kpicreatives.com/oscar

Marco — autonomous outbound agent

Infrastructure + signals + research + email/LinkedIn · human-in-the-loop

Marco builds the sending layer first: secondary domains, SPF/DKIM/DMARC, mailboxes, warm-up, placement tests, per-mailbox caps, and reputation monitoring. The same control plane is designed to scale from one mailbox to a thousand. No campaign launches until its senders clear the deliverability gates.

Then it finds the right moment, not just the right job title. Marco searches across commercial databases, LinkedIn, company sites, job boards, industry directories, and public or first-party data. It looks for signals such as leadership changes, hiring, funding, website intent, and new permits. It scores and deduplicates prospects, researches each company, then writes a short message in the sender's voice. Email and LinkedIn sequences run automatically; Marco triages replies every 15 minutes and flags positive intent in Telegram. Factual claims, pricing, and objections stay behind human approval.

A human operator no longer has to choose between depth and volume. Signals decide who and when; research decides what to say; infrastructure makes sure it arrives. Every send and reply becomes data for the next campaign.

Behind the Watt — AI with receipts

Open data + evidence pipeline · public records, LLM extraction, human approval

An open database tracking which behind-the-meter power projects at data centers are actually operating. Watchers monitor permits, filings, and public registries; the pipeline archives each source, uses AI to extract and cross-check claims, then holds publication for human approval. Every fact retains source-level provenance and is exposed through CSV, JSON, OpenAPI, and read-only MCP.

AI handles the volume, but the model is never the source: every published claim stays inspectable.
behindthewatt.com GitHub source

ADUscale — voice AI acquisition machine

Co-founder & CEO · built the product solo

A marketplace for ADU construction: complete information architecture, programmatic pages, structured data — plus the full acquisition machine behind it: funnel, voice AI agent answering inbound calls (Vapi), CRM integration, and analytics. Business thesis to production, no handoffs.

Positioning, funnel, voice agent, CRM, code, deploy — one person, working in production.
aduscale.com

SaaS → self-hosted migrations

FinOps by owning the infrastructure

Moved recurring vendor tools onto self-hosted open source I selected, deployed, and integrated: Frame.io → FreeFrame, DocuSign → Documenso, Attio/GoHighLevel → Twenty CRM, Calendly → Cal.com. I run the whole layer — Docker, reverse proxy, TLS, backups — plus invoicing automation wired into Mercury.

Cuts recurring subscription spend and keeps the data in-house.

InspectPilot

Construction compliance engine · built by a developer under my direction

A concierge agent for general contractors that files and schedules building inspections with LADBS — on top of a compliance engine scoring every contractor on how they actually perform: first-pass rates, violations, permit history. Runs on ~11 million data points covering every LA inspection over 13 years.

11M public inspection records turned into a contractor-quality signal — trust backed by data, not reputation.
inspectpilot.ai

DirectorMode.AI

Creative-director-as-a-service · product owner / technical direction

An AI that actually watches and listens to a video — footage, audio, pacing, hooks — and grades the edit against two rulebooks at once: the brand's and the mechanics of viral performance. A clear score, a director's note, and a timecoded fix list before you publish.

Know whether a video will land with its audience — before you publish.
directormode.ai

The same patterns, installed into your business

Four packaged installs built from the systems above — fixed scope, built on your stack, owned by you.

For general contractors

SubPilot

The AI sub dispatcher that lives in your phone: confirmations, rescheduling cascades, bid coverage with leveling, inspection corrections, and compliance paperwork — dispatched from your own number, with your approval on anything that matters.

korets.net/subpilot
For home service contractors

Revenue Recovery System

Finds the revenue leaking out of an HVAC, plumbing, or electrical shop — unsold estimates, missed calls, a silent customer base — and installs the system that recovers it: AI follow-up, 24/7 front desk, database reactivation.

korets.net/revenue-recovery
For owner-led tax and accounting firms

Tax Operations Core

A dedicated operating layer connecting client communication, IRS transcripts, documents, tax software, and billing. It starts with one bounded workflow, keeps the professional tax suite in place, and expands only after the firm measures the economics.

korets.net/blackink
For mid-market operators · property management, construction, multi-entity groups

AI-First Twin

Most established companies won't survive a frontal AI transformation — the org resists it, and it should. The move that works: build the AI-first twin of one core process as a sidecar. Small, separate, no threat to the team that runs today's business — until the twin proves out and grows into the main line. I design and build the twin, install the human approval gates, and hand your people the keys. Fixed scope, measured against the process it mirrors.

Start the conversation

Have a process that leaks time or margin?

If it runs on phone calls, spreadsheets, and chasing people — it's a candidate for one of these patterns. Custom engagements start with a one-week audit of how the money actually flows.

Book a call