AI Product Manager
shipping at scale.

How I work

1. 01
   Simplify ruthlessly. ICC dispatch: 22 commands → 1, US patent. UKPass: 5-tab feature buffet → 3-tab guided experience. MoleSafe: 2-hour patient imaging → 20 minutes; per-lesion diagnosis → 7 seconds. The job isn’t adding features — it’s deleting them with intent.
2. 02
   Customer obsession is field work — physically. For MoleSafe I rented mannequins, set up a stopwatch, and reproduced the competitor’s workflow end-to-end in the office; every step over a second got tagged for elimination. For ICC I rode along on 911 calls and ran design-thinking sessions with first responders before writing the integration spec. For DermDx I travelled to Australian clinics — the world’s highest melanoma incidence per capita — before proposing architectural changes.
3. 03
   Process is the product. When a four-person team has to outrun a hundred-person team, the cycle has to compress. I designed the AI Product Development Lifecycle at Valsoft — 55 agents, 26 skills, 5 orchestrators, typed handovers, quality gates — and ran it to ship 7+ major launches in six months at ~10× conventional velocity. Process is the unfair advantage when the team isn’t.
4. 04
   Own the data and the workflow. DermDx ran a multi-year FDA submission and the platform roadmap on the same source of truth — model improvements landed in submission packets within days. The AI Support Agent’s 5-layer safety pipeline (PCI guard, PII redactor, hallucination guard, output guard, escalation gate) was non-negotiable from the first PRD, not bolted on after a demo. Models get replaced; the pipeline and the workflow don’t.
5. 05
   Ship complete, not MVP’d. Indie iOS apps (UKPass, CANPass, FAA Part 107 / PPL) ship with full feature parity at v1.0 — no MVPs, no staged rollouts, no v0.x.y backlog. The alarm-to-PSAP integration on Spillman Flex went live across three states during COVID after seventeen protocol iterations. roomMaster Web App launched and DAU jumped 700% on day one because the Housekeeping PWA had already pressure-tested the API end-to-end. Tight constraints make the design choose itself.

Product Management playbook

A living mind map of the seven-stage product lifecycle I run by default — Discover, Define, Design, Develop, Deliver, Debrief, Depart — with the artifacts and activities that anchor each stage. Each stage has its own typed outputs (intent docs, PRDs, ADRs, work breakdowns, launch plans, retros, sunset comms) and quality gates between handovers, so a feature never moves forward on a meeting; it moves on an artifact.

Built over years of shipping in regulated AI, healthcare, and hospitality, then continuously edited as the work taught me what to keep and what to throw out. The MoleSafe redesign, the DermDx FDA submission, the AI PDLC at Valsoft, and every indie iOS release all ran through this same skeleton — different domain, same backbone.

The lifecycle includes Depart on purpose. Most PM playbooks pretend products don’t end; mine has the sunset, the migration plan, and the comms template in the same artifact as the launch. Treating the end as a first-class phase is what lets you ship the next thing without dragging the old one along.

AI Engineering map

The companion to the PM playbook, on the engineering side. Models, evals, retrieval, agent topologies, prompt patterns, tool-use loops, observability, safety, eval harnesses, cost accounting, inference routing — the surface I actually work across when an AI feature has to ship to production rather than sit in a demo. Intentionally tall; click to expand and pan, the lightbox loads it at original resolution. This is how the AI PDLC (55 agents, 26 skills, 5 orchestrators), the AI Support Agent’s 5-layer safety pipeline, the AI Concierge’s tool-using booking agent (+35% bookings, +60% CSAT), and Ampliphi’s hybrid forecasting + LLM pricing layer all came out of the same head — different products, same engineering map. Every node has to earn its place by showing up in a discover-to-depart artifact on the PM playbook above; otherwise AI work drifts into “we have an LLM somewhere.”

Speaking

Webinar · Xmind

Xmind Playbook · Building a Mind Palace with Xmind

Xmind Ambassador for visual thinking — one of a small global cohort recognized by the Xmind team for using mind-mapping at scale across product, AI engineering, and personal knowledge management. Recent webinar with the Xmind team on building a mind palace — the practice that turns hundreds of books into a queryable second brain, and the same practice that produced the PM playbook and the AI Engineering map above. Available for talks, workshops, and webinars on AI Product Development Lifecycle, agentic systems, and the visual-thinking craft.

Off the clock

I read like it’s the job. Hundreds of books across engineering, AI, mathematics, cognitive psychology, economics, and systems design — not background noise, but how I build mental models fast enough to navigate domains I’ve never worked in before. Each book gets mind-mapped, cross-linked into the larger palace, and pulled back when the next problem walks in.

Seven indie iOS apps and counting — the citizenship-pass series (CANPass, USPass, UKPass, AUSPass), the FAA Part 107 / PPL exam simulator, FoodPass, and MindQuest. Each one shipped solo, end-to-end, with the same playbook the cases on /work were built with. The indie work is the test rig where the playbook gets stressed in isolation — no team to compensate for a weak spec, no PRD buffer, just the playbook and a deadline. Open-source contributor to ScreenPipe. Vancouver, BC. Canadian citizen.

The career, mind-mapped

Open the live Prezi

The deck · hosted on Prezi

Mykola Kotliarenko — Portfolio

A zoomable timeline across public safety, healthcare AI, and hospitality.

prezi.com/p/a7--cshc6iuu

If the AI Engineering map and the PM Playbook above are how I structure problems, this Prezi is how I structure my own story. Same Mind Palace technique, different content — three eras (Motorola public safety / MetaOptima healthcare AI / Valsoft AI PDLC), the throughlines drawn explicitly between them, and a camera that pans through the connections instead of asking you to scroll past them.

It’s also the strongest single demonstration of the visual-thinking craft I claim elsewhere on this page. The Xmind Ambassador work, the playbooks, the case-study mind maps — they all came out of the same practice that produced this canvas. If you want to see how I’d frame a complex decision in a room, this is closer to the live experience than anything written.

Where I’ve shipped

Background