01 / 03
Guest-facing agents
Inquiries and bookings answered in seconds, in your customer's language.
Like Ranger, below.
// AI BUILD TEAM · EMBEDDED WITH YOUR BUSINESS
Two weeks.
One working AI agent.
Live in your business.
Two of our engineers embed with yours and ship your first AI agent in two weeks.
$300M+ moved through systems we built · Front page of Hacker News (470 upvotes) · Top 1% Upwork
14+ YRS
// Building software for other people's businesses
50+
// Projects shipped — every one live
3 VENTURES
// Of our own, run on AI we built
// WHERE AI FITS
Most owners know AI matters. Few know where it fits in their business.
Asking "where can we use AI?" gets you a chatbot nobody opens.
If twice as many customers came through your door tomorrow, where would your business start breaking? That's where we start.
Pick a bottleneck. We build the agent.
02 / 03
Ops & back-office agents
Scheduling, quoting, the routing that eats your team's week.
Like Mara's ops agent, below.
03 / 03
Autonomous decision agents
Pricing, restocking, the judgment calls your team makes all day — faster and more consistent.
Like Pear, below.
// THREE WE RUN LIVE
Two we built for clients. One we built for ourselves.
Click into any of them — they're live.
Mara Hilltop · safari lodge
An AI agent that runs a safari lodge in the Maasai Mara.
Ranger handles guest inquiries, quotes, and bookings 24/7; a second agent runs reservations, check-ins, and pricing through chat. Hours of daily manual work gone — inquiries in seconds, not days.
Visit ↗ Custom MCP server · multi-model · PMS
R
Ranger
Mara Hilltop · online
LIVE
Pear Protocol · Agent Pair
An AI agent that trades perpetuals on signals and sentiment.
Watches more signals than a human can, and manages long/short positions on its own. Live on Arbitrum & HyperEVM for 2+ years.
Visit ↗ On-chain · sentiment pipeline · risk engine
Agent Pair · Signal
Sentiment divergence +2.4σ · entering pair
SlopIt · publishing
A blog platform where the AI agent is the user.
Prompt to live URL, no human in between. Every post on this site ships through it.
slopit.publish({
title: "Why remote work wins",
body: "...",
tags: ["remote", "work"]
}) → 200 OK · 142ms
Live at nj.slopit.io/why-remote-work-wins
// HOW IT WORKS
Forward-deployed engineers.
Not a vendor. Not an agency.
AI doesn't fail at the model. It fails where an engineer's assumptions meet how your business actually works — and that's the gap we're here to close.
01
A real conversation, free
45 minutes with NJ. Where AI helps you, and where it doesn't yet. No deck, no proposal-by-PDF.
02
Week 1 discover, week 2 ship
An agent live in your environment, doing real work. Fixed price, fixed scope, in your repo.
03
We keep going, or we don't
If it works, the next piece. If it doesn't, you're not locked into anything.
// PRICING
Clear pricing. No discovery call to find out what it costs.
An in-house version of this — two AI engineers — is a six-month search and $300K+ loaded comp each. This is two engineers, already a team, ready to start.
Start here
AI Build Sprint
$12,500
Two weeks to a live agent in your environment. Fixed price, fixed scope, in your repo. 30 days of support.
If we can't find at least one high-ROI opportunity on the first call, we don't take you on.
Start a sprint →Embedded AI Team
$10,000/mo
A new agent every month, two engineers on your team. Two-month minimum, cancel anytime after.
Talk to us →Start with a sprint. Keep us embedded if it works.
// THE TEAM
No account managers. No layers. You work with the people who build.
Founder & Chief Architect
NJ
Penn State hackathon winner turned Silicon Valley builder. NJ has spent 14 years shipping software for other people's businesses: crypto since 2014, top 1% on Upwork, $300M+ moved through systems he built, and now AI. He also runs a safari lodge in Kenya, and he picks up the phone.
Direct line California · +1 (717) 683-9393 · call or WhatsApp
Senior Engineer & Delivery Lead
Deep
Leads client delivery end-to-end. The person who makes sure your system works in production, not just in a demo.
Senior Engineer & Systems Architect
Pranjal
ex-Swiggy. Our go-to for the hardest problems: Web3 infra, AI systems, anything where “figure it out” is the spec.
Full-Stack Engineer (Design Lead)
Chetan
Full-stack with design instincts. Most of our UI passes through him before it ships — and increasingly the AI integrations underneath it.
Full-Stack Engineer (Backend / Performance)
Hemanshu
Backend-first full-stack. Built a 250 req/sec layer behind one of our hospitality systems. Owns caching, API design, the parts that have to scale under load.
// WRITING
While I slept, a 5-year-old MacBook indexed a year of video locally — front page of Hacker News, 470 upvotes.
// LET'S BUILD
You don't need an AI strategy.
You need AI that's working.
Tell us one thing in your business you wish ran itself — honest answer within a business day on whether AI can do it.
Looking for a strategy deck, a 6-month roadmap, or the cheapest chatbot? We're not it.
Or skip the form Call or WhatsApp NJ at +1 (717) 683-9393. He picks up.
// Thanks — received
We'll be in touch within one business day from nj@simbastack.com.
// Couldn't send
Something went wrong on our end. Email nj@simbastack.com directly and we'll pick it up.