Clarify the use case
Together we assess the process, value, data and risks. Then we decide what is worth building and what is not.
Prioritized scope · Feasibility · Delivery plan
Germany / EU / US · Remote
Working with me
I take projects from problem to production.
I have built digital products since 2015 and worked independently since 2018. I work directly with founders, business teams and engineers in German or English, across Germany, the EU and the US.
- Engagement
- Independent · Project or interim
- Focus
- AI, automation and digital products
- Region
- Remote · Germany, EU and US
Reference
“In our network, he has an outstanding reputation. Personally, I can say that he is a one-man army. He's pragmatic, solves problems efficiently, and has the right experience.”
Thomas Marbella
Founder & CEO, OneCode GmbH
Original conversation
Tailorwine & Founders League
A conversation about Tailorwine and the work behind the digital product.
Watch on YouTube ↗Independent AI Consultant & AI Product Consultant
AI consultingthat ships.
I find the AI use cases that pay for themselves and build the systems that take real work off your team.
From process analysis and prototyping to integration and production. For companies and product teams that need AI to do useful work, not just look good in a demo.
IndependentRemote Germany / EU / USGerman / English
Project briefdelivery
- Engagement
- AI consulting + delivery
- Scope
- Process · Product · Integration
- Outcome
- System in production
Definition of done
It runs in production. The owners understand it. The team can operate it.
ElectaCar
3 days
to a working first version
ElectaCar
6 weeks
from kickoff to production
Syntax Institut
3 months
from concept to first paying customers
VOXR
7 / 10
of the largest DAX companies use the product
The elephant in the room
AI demos are easy. Making one useful, reliable and worth the cost is the real work.
The model is rarely the bottleneck. Data, rules, permissions, integrations, failure modes and ownership are. Most of that stays invisible until something breaks.
What people see
Model, prompt, demo
What has to work
- Data and business rules
- Permissions and integrations
- Approvals and error paths
- Monitoring and ownership
That is the gap I close: from a convincing demo to a system people can rely on.
What I take ownership of
From an open problem to a working system.
I keep consulting and implementation together. Nothing gets lost in handoffs, and every decision is tested against the real product.
Build the workflow
Connect business logic, AI decisions, APIs and existing systems into a reliable workflow.
Prototype · Integrations · Approval and error paths
Put it into production
I roll out the solution, monitor it and document it so your team is not dependent on one person.
Deployment · Monitoring · Documentation · Handover
When I am useful
Problems I usually step into
- 01You have an AI use case, but nobody owns both the scope and the build.
- 02A manual process is slowing growth, margin or response times.
- 03A digital product needs temporary product and engineering ownership.
How I work
An agent is not a business process.
Reliable automation needs clear rules, limited permissions and controlled handoffs. AI belongs only where fixed logic cannot do the job.
The result is not another demo chatbot. It is a traceable system that handles real work.
How a process becomes a systemRules, control, operations
- 01
Input
Data, request or manual process
- 02
Rules
Validation and fixed business logic
- 03
AI
Only where context and judgment are needed
- 04
Approval
Human control for critical steps
- 05
Operations
Logging, monitoring and clear ownership
API & dataLogs & error pathsHandover & operations
Selected projects
I do not stop at advice. I ship.
Product ownership, architecture and implementation in one engagement. The result is working software, not another presentation.
01↗
ElectaCar
AI Product Consultant / Lead Product Engineer
3 days to the first build. 6 weeks to launch.
Product, architecture and implementation of an EV platform with structured vehicle search, data imports, AI-assisted research, insurance matching and admin workflows.
02↗
FAMFAM
Senior Frontend Developer
12,000 users at launch. Top 10 in the App Store music category.
Built the event and community app from concept to launch in a team of more than ten people, including flows for events, guest lists, reservations, content, profiles and donations.
03↗
Syntax Institut
Lead Product Engineer
Paying customers after 3 months.
Built the B2C learning platform from concept to launch and ongoing operation, including architecture, frontend, backend and core integrations.
04↗
Tailorwine
Product Manager & Senior Full-stack Engineer
The B2B MVP helped win REWE and EDEKA.
Designed and built the digital sommelier as a commercial B2B product.
05↗
Rivoara + Runtime Affiliate
Founder / Product Owner & Builder
Commerce and affiliate operations in one system.
Built multilingual D2C journeys and a multi-tenant platform for creator onboarding, Shopify attribution, commissions, analytics and payouts.
06
VOXR
Chief Technology Officer
Used by the German federal government and 7 of the 10 largest DAX companies.
Led product and engineering for interactive live events and designed the system for unreliable connectivity.
07↗
Heyamigo
Creator / AI Product Engineer
2,186 npm downloads in 30 days.
Open-source AI assistant for Claude, Codex and Grok with persistent queues, memory, browser delegation, reminders and voice workflows.
Technical implementation
I can advise, architect and build.
If the bottleneck is the data model, API, frontend, agent logic or production setup, I can take it on directly. The stack serves the product, not the other way around.
AI systems & agents
Agent logic, tool calls, memory, browser automation and evaluation.
OpenAI · Anthropic · Grok · Tool Use
Web & product
Production-ready interfaces, admin flows and internal tools.
TypeScript · React · Next.js · Node.js
Data & integrations
Data models, APIs, commerce and content systems.
PostgreSQL · SQLite · Strapi · Shopify · GraphQL
Operations
Queues, cron jobs, error paths, logging and monitoring.
Vercel · Webhooks · Background Jobs · Cron
What this changes
Architecture decisions are made against the live system, then implemented by the same person. No gap between the advice and the build.
A real project?
Show me the work your team still does by hand.
Two or three sentences about the current process, the outcome you need and the timeline are enough. I will tell you directly whether I can help and what I would do first.