# SimbaStack > SimbaStack is a small AI engineering team for founders and product teams. We build AI features alongside your team, wire them into your systems, and keep them working after launch. Founded by NJ Singh — 14 years building production software, top 1% on Upwork, $300M+ moved through systems built. Team across the US, India, and Kenya. ## What we are SimbaStack is a forward-deployed engineering team: in your repo, your systems, your standup. We take an AI feature from a working demo to something that handles real customers, real data, and real edge cases, and we keep improving it in production. The thesis: AI doesn't fail at the model. It fails where an engineer's assumptions meet how your product and your customers actually behave. Working inside your team is how we close that gap. ## What we build **Customer-facing agents.** Chat, WhatsApp, voice, in-product assistants. Wired to your real inventory, orders, and accounts, with hard limits on what they can do without a human. **Internal workflow agents.** Ops, quoting, scheduling, back-office. The work your team does by hand today, with a person approving the steps that matter. **Decision systems with guardrails.** Pricing, trading, routing. Language models where they help, deterministic code wherever money or correctness is on the line. ## How we work **A real conversation, free.** 45 minutes with NJ on what you're building and where it's stuck. Where AI helps, where it doesn't yet. No deck, no proposal-by-PDF. **Scope it, then ship it.** One workflow, agreed acceptance criteria, access sorted up front. Two weeks for a bounded first build, longer when the scope says so. Fixed price, in your repo. **We keep going, or we don't.** If it works, the next piece on your roadmap. If it doesn't, you're not locked into anything. ## Services - **AI Build Sprint — $12,500.** Two weeks to a working AI feature in your environment. One workflow, agreed acceptance criteria, in your repo, 30 days of support after launch. Bounded scope by design: multi-system builds, complex permissions, or production-critical paths get scoped and priced on the first call. If we can't see a clear first build on that call, we'll say so and won't take the sprint. - **Embedded AI Team — $10,000/month.** Two engineers embedded with your team, NJ on technical direction. We own what we've shipped, watch it in production, and work your backlog every month. Two-month minimum, cancel anytime after. Already have a roadmap? Skip the sprint and start here. ## Production work ### Mara Hilltop — AI guest agent for a safari lodge (our own lodge, runs on KaribuKit) - **Stack:** KaribuKit PMS · custom MCP server · multi-model - **Problem:** Small team, everything manual. Guest inquiries arriving at 2am. Staff buried in ops instead of guest experience. - **What we built:** Ranger, a guest-facing agent on the lodge website that answers inquiries around the clock, quotes from live availability in the guest's language, and hands staff a ready-to-confirm booking. A staff-side copilot runs reservations, check-ins, and pricing through chat. Confirmation and payment stay with a human by design. - **Our role:** Our own lodge, not a client. We built KaribuKit, the property system underneath, and we live with every edge case. - **Live:** https://marahilltop.com/ ### Pear Protocol — Agent Pear, AI trading agent (client) - **Stack:** Multi-model DAG · on-chain + sentiment pipeline · confirm-before-execute - **Problem:** Traders had more on-chain data, sentiment, and pair signals than any person can watch, and no way to act on them quickly without giving up control. - **What we built:** Agent Pear answers pair and market questions from live on-chain stats and sentiment, then stages long/short perpetuals positions that execute only after the trader confirms. Live for Pear's retail traders on Telegram and web. - **Our role:** Two years as Pear's engineering partner. $300M+ has traded through the platform we helped build. - **Live:** https://pear.garden/ ### SlopIt — agent-native publishing platform (ours) - **Stack:** TypeScript · MCP · REST · Static HTML - **Problem:** Existing blog tools assume a human at the keyboard — OAuth flows, draft UIs, image uploads. AI agents trying to publish hit a wall of human-shaped friction. - **What we built:** A publishing platform with the agent as a first-class user. Tell Claude or ChatGPT to publish a post, the agent calls the MCP tool, and a live URL comes back in seconds. - **Result:** Zero human steps from AI prompt to live URL. Open-core, live at slopit.io. - **Live:** https://slopit.io ## Team - **NJ Singh** — Founder & Chief Architect. Penn State hackathon winner turned Silicon Valley builder. 14 years shipping software for other people's businesses: crypto since 2014, top 1% on Upwork, $300M+ moved through systems built, and now AI. Also runs a safari lodge in Kenya. Picks up the phone. - **Deep** — Senior Engineer & Delivery Lead. Leads client delivery end-to-end. - **Pranjal** — Senior Engineer & Systems Architect (ex-Swiggy). - **Chetan** — Full-Stack Engineer (Design Lead). - **Hemanshu** — Full-Stack Engineer (Backend / Performance). ## Notable writing ### While I slept, my 5-year-old MacBook ran Gemma 4 locally and indexed a year of video (May 2026) A local-LLM pipeline that indexes a year of video on consumer hardware — a 2021 MacBook running Gemma 4 with 50GB swap. Open-sourced as framedex (MIT). Front page of Hacker News for ~30 hours, 470 upvotes, 142 comments. - **Read:** https://blog.simbastack.com/indexed-a-year-of-video-locally/ - **Discussed on Hacker News:** https://news.ycombinator.com/item?id=48222733 ### We rebuilt the structured output problem one layer up (May 2026) History of the structured-output era and the tool-calling era; argument that the same coercion pattern is repeating one stack-layer up. - **Read:** https://blog.simbastack.com/we-rebuilt-the-structured-output-problem-one-layer-up/ ## Contact - Email: nj@simbastack.com - Phone / WhatsApp: +1 (717) 683-9393 - LinkedIn (NJ): https://www.linkedin.com/in/singhniranjan/ - X / Twitter (NJ): https://x.com/bozo_eth - Upwork (NJ, top 1%): https://www.upwork.com/freelancers/niranjans