This isn't a demo.
This is how I work.

Everything I ship runs through STEEPWORKS.

Running in Production

Victor's Production Stack

These workflows run daily. Not demos—real systems you can clone.

Image Generation

30 seconds. Your brand. No Canva.

Concept → PromptSpec → Branded visual in 30 seconds.

30secconcept to finished image

Full GTM Intelligence

Ask your CRM anything. Get answers, not exports.

CRM connection → Deal data → MEDDPICC extraction → Pipeline analysis.

DirectCRM to Claude connection

3 Newsletter Brands

3 brands. 1 pipeline. Zero manual curation.

Baltimore Families + DMV Families + STEEPWORKS Weekly — multi-brand newsletter automation.

3newsletter brands, 1 pipeline

ICP Builder

9 agents build your ICP from evidence

Upstream agents collect market, customer, and competitive data. Downstream agents score and rank accounts.

9coordinated agents
USE CASE 1

BMOREFAMILIES.COM

A live city site. 100+ sources. 313 venues. Real subscribers.

  • •Multi-source scraping pipeline (Firecrawl + custom scrapers) ingests events from 100+ sources
  • •Multi-agent curation — 5 persona agents debate which events to feature
  • •Full stack: Supabase + Cloudflare Workers + Next.js + Vercel
  • •Weekly Beehiiv newsletter generated and distributed automatically
Visit bmorefamilies.com
BmoreFamilies.com homepage — live city events site built with STEEPWORKS
STEEPWORKS

Video coming soon

Multi-Agent Newsletter Pipeline

7 agents debate 120+ articles weekly

USE CASE 2

STEEPWORKS NEWSLETTER + DAILY FEED

7 agents debate 120+ articles weekly. You get the verdict.

  • •65 RSS feeds ingested and scored daily
  • •7 persona agents independently evaluate each article
  • •3-round moderated debate produces the weekly newsletter
  • •Total cost: $6-8 per issue
NewsletterDaily Feed
USE CASE 3

THIS WEBSITE

You're reading copy generated with STEEPWORKS.

  • •/produce-content drafted the initial messaging
  • •/skeptical-buyer critiqued it from your perspective
  • •/edit-content applied voice standards and AI-detection prevention
  • •Copywriting skill refined headlines and CTAs

(And I've spent days looking at it personally too.)

STEEPWORKS

Video coming soon

Website Copy Generation

Watch the full content production workflow

USE CASE 4

INNOVATIVE SIDE PROJECTS

What happens when you point a Knowledge OS at something that isn't GTM?

Handbook for Living

I built AI agents for Jesus, Buddha, Confucius, Muhammad, Laozi, and Zoroaster — each trained on 23,000+ verified historical utterances. Then I told them to write a book together.

Six traditions that spent millennia in separate rooms produced prose that reads like a single voice. The result was astoundingly beautiful. And weird. And somewhat disappointing. Which is exactly what real building looks like.

  • •6 persistent agents with cross-session memory
  • •23,442 utterances across scholarly-verified corpus
  • •Same Knowledge OS architecture — different domain entirely

Proof this system works beyond sales decks and pipeline reports.

GitHub RepoRead the full story
STEEPWORKS

Video coming soon

Handbook for Living

6 prophets. 23,000 utterances. 1 book.

STEEPWORKS

Video coming soon

GTM Operations

Daily workflows running at scale

USE CASE 5

ACTUAL SEED/SERIES A GTM OPS

STEEPWORKS runs daily GTM operations:

  • •Prospect research before every sales call
  • •Weekly competitive intelligence updates
  • •Actual blogs, whitepapers, newsletters
  • •Call synthesis from every customer conversation
USE CASE 6

STEEPWORKS PRODUCT BUILD

This product was built with itself.

Battle-Tested

10-12 hours, every day

Hard-won lessons passed on.

Constantly Iterated

Real work, real edge cases

Every skill broke. Then got fixed.

Self-Improving

Meta agents

Claude trained to make itself better.

I put in the work so you don't have to.

I don't demo STEEPWORKS. I use it.

Demos are optimized for showing. This system is optimized for shipping.

Get STEEPWORKS