Built for teams in
What we do
We map your workflows and find where AI actually pays off - and, just as importantly, where it doesn't. You leave with a ranked, costed shortlist, not a wish list.
We build LLM features, agents, and automation into the systems you already run - CRMs, ERPs, internal tools, and data pipelines. Working software, in production.
When off-the-shelf doesn't fit, we build the internal tools that do: copilots, document pipelines, and evaluation harnesses tuned to your domain.
We leave your team more capable than we found it - training, governance, and ongoing fractional AI leadership so the work keeps compounding after we go.
How we work
We learn how your business actually runs and pinpoint where AI earns its keep. One to two weeks.
We ship a working pilot against the highest-ROI opportunity - real data, real users, in weeks.
We wire the proven pilot into your systems with monitoring, guardrails, and evaluation in place.
We train your team to own it and stay on as advisors for as long as it's useful.
Why Derkins Labs
We're not reselling a platform. We pick the model, stack, and build-vs-buy that fits your problem - and tell you when the answer is 'don't build this yet.'
The people who scope the work are the people who ship it. You get working software wired into your systems, not a deck and a follow-on proposal.
Data boundaries, access, retention, and evaluation are designed in from day one - because AI touching your real operations has to hold up under scrutiny.
About
Derkins Labs is a small, senior team of engineers who build AI into real operations. We're not a reseller - we scope the work we'll build, then build it, wired into the systems your business already depends on.
We take on a small number of engagements at a time so the people you meet are the people who do the work. When we're done, your team is more capable than we found it.
Martin Gottweis
Founder & Principal Engineer · previously Meta, Booking.com
Before Derkins Labs, Martin spent five years at Meta in New York as a technical lead on AI personalization and integrity systems: the graph-RAG infrastructure behind messaging search for roughly 500 million users, knowledge injection for WhatsApp AI, and enforcement infrastructure running at over eight billion queries per second.
Before that he was a senior developer at Booking.com in Amsterdam, where he led the hotel page, the core revenue funnel, and shipped 0-to-1 products in its new-ventures division. He has written production software since 2007 and holds a master's degree in aerospace engineering from the University of Zilina.
Tell us what your business does. We'll show you where AI pays off - and how we'd build it.