Roman Martins
I build with AI agents — and teach experienced engineers to do the same.
15 years shipping physical products — LEGO, industrial machinery — then four years building AI systems that do real work. Today I run product development, research, and content with a team of agents, and I show experienced engineers how to do the same.
your experience, multiplied.

AI Agents for Engineers
A free community where experienced engineers learn to build with AI agents — real builds shared as they happen, live office hours, no hype.
Join free ->Forward-deployed AI builder
I embed with domain teams, find the manual work, and ship the agent that removes it. See the projects, career arc, and operating model.
Review proof ->Forkable Factory
Weekly probes, benchmarks, and shipped agentic tools exploring how physical product development becomes forkable.
Open lab ->Current Labs
Live experiments under one thesis.
I build AI-powered operating systems for complex work. The flagship lab applies agentic workflows to physical product development. The second proves it with evidence – fact-checking an entire industry against its own press releases, every number linked to a primary source.
Forkable Factory
A public exploration of how agentic workflows can move physical product development from concept to manufacturing handoff. Probes, benchmarks, maps, and shipped tools make the thesis concrete.
The Humanoid Ledger
What is verifiably true about humanoid robots in manufacturing. Wall Street says $7 trillion; the factory floor shipped 16,580. Every notable deployment evidence-graded, every number linked to a primary source.
AI Agents for Engineers
Everything on this site was built by one person with a team of agents. The community is where I show experienced engineers how — real builds, live office hours, no hype.
your experience, multiplied.
Method
How I build AI operating systems.
The craft is not prompting. It is turning expert work into a system with memory, cadence, judgment, and review.
Map the real workflow
Start with the human operating rhythm: inputs, handoffs, judgment calls, bottlenecks, and failure modes.
Find the leverage points
Separate where AI should decide, draft, retrieve, critique, summarize, or simply stay out of the way.
Design the agent loops
Turn recurring work into repeatable commands, prompts, trackers, and review loops that can be run every week.
Build the workspace
Codex, Claude Code, Markdown, Git, APIs, and lightweight UI where useful. The system should be usable, inspectable, and adaptable.
Measure execution
Track the work that matters: applications, outreach, shipped artifacts, decisions, blockers, and next actions.
About
Operator roots. AI hands.
Systems thinking for agentic work.
I started in physical systems: factories, industrial equipment, global engineering teams. Then I spent years building AI products, automation systems, and agentic workflows. The through-line is turning messy expert work into operating systems people can actually use.
Career Arc
Leading a 10-person cross-functional product development department. Responsible for new product development and lifecycle upgrades of complex industrial equipment across Europe and China.
Led product strategy for a personalised AI-powered publishing platform. Built end-to-end AI workflows, prompt architectures, and QA systems – scaling to 1,000+ books produced. Also ran an AI automation agency building custom GPT-based systems for business clients.
Led cross-functional engineering teams delivering complex industrial and manufacturing solutions for global clients. Drove advanced manufacturing initiatives including additive manufacturing, aligning engineering execution with business strategy.
Grew from injection molding technician to Lead Professional in LEGO's Concept Factory. Led manufacturing innovation initiatives, established new technological test environments, and coordinated global engineering teams.
How I Work
Tools & Stack
Proof
Proof tracks, not a project archive.
The signal is not that I built many things. It is that the same operating model shows up across professional workflows, physical systems, and revenue products.
AI workflow systems
I turn recurring expert work into command centers, scoring loops, and AI-assisted operating rhythms.
Proves I can design the workflow, build the tool, and make AI useful inside a real decision process.
The Wire
Automated daily product-intelligence feed across AI dev tools and manufacturing — sourced, scored, and published by an agentic pipeline.
Stakeholder Lens
Paste a roadmap once and generate audience-specific views for engineering, sales, execs, and customers.
Implementation Scoping Tool
Describe a business problem, answer discovery questions, and receive a structured AI implementation scope.
Industrial and physical systems
I apply agentic workflow thinking to manufacturing, CAD, product-development, and operations problems.
Proves I can work where software meets physical constraints, suppliers, APIs, compliance, and operational reality.
Agent CAD Probe
Weekly benchmark of AI-native CAD tools, scored on agent-readiness, evidence quality, and workflow maturity.
Photo-to-Print Benchmark
Drop a photo, generate printable STL candidates, and score image-to-3D models on printability.
Forkable Factory Map
Public map of the 10 product-creation phases and how far each can already be made forkable with agents.
Founder and revenue products
I have shipped products beyond demos: AI pipelines, fulfilment, customer-facing experiences, and revenue.
Proves commercial judgment, scrappy execution, and the ability to move from concept to live product.
Personalised Children’s Book Platform
AI-generated personalised stories and illustrated pages routed through print-on-demand fulfilment.
Downtime Cost Calculator
Manufacturing ops calculator that turns incident data into downtime cost, annual risk, and monitoring ROI.
Roman's Lab
The wider collection of PM tools, AI workflow prototypes, manufacturing experiments, and shipped utilities.
Forkable Factory
the weekly signal report on agentic manufacturing.
every Tuesday: 5 signals · 1 leaderboard delta · 1 tactic · 1 keyword to watch · 5 min read
by Roman Martins · building the Forkable Factory
Contact
Let's build an AI workflow
that actually survives contact.
Open to forward-deployed AI work — embedding with a team, finding the manual work, shipping the agent that removes it — plus consulting pilots and conversations with engineers crossing into agents.