Automate the work
your team repeats
Automation run · server-setup
Runs and reports are examples with made-up names. The cases are real work, anonymized. Every result line links to the product behind it.
The foundation for a business that runs on automation
Agents and integrations that do the repetitive work, security that keeps it safe, one developer who keeps it running. A fixed scope per step, nothing deployed without a rollback.
Automate the repetitive work, build what is missing.
Know where you stand before anything is touched.
Keep it secure, backed up and documented.
Brands I have built for, tools I build with
In employment at agencies and product companies before 2024, and as a freelancer since. The tools are the ones in daily use, not a wish list.
What I build
Twelve services with a fixed shape, automation first. Each one leaves a document in your repository, not only a result on a server. See what you hold afterwards →
AI Integration
Agents, custom skills, MCP servers, RAG over your data. One use case to production.
Integrations
Systems that talk to each other reliably: bookings, payments, ERP, mail.
Full-stack Build
Design, architecture, backend, front end, API, hosting: a new application built end to end.
Modernization
PHP, framework, database, web server and hosting brought up to date, while the system keeps running.
Android App
Kotlin and Jetpack Compose, on your API or a new Laravel backend.
Health Check
Two-day assessment: automation opportunities, risks, a step-by-step plan.
Security Assessment
Vulnerability assessment or application pentest, with a retest.
Architecture Review
Options compared, a written recommendation, decision records.
Hardening and Secure Pipeline
Attack surface closed, security gates in CI, backups that restore.
Maintenance Retainer
A monthly hours block: patches, monitoring, small changes, a report.
Compliance Alignment
NIS2, GDPR and DORA: gap analysis, remediation, evidence.
Handover Pack
Runbook, architecture, decisions, accounts, risks. Yours to keep.
Phalcon to Laravel, module by module, while the platform stayed in daily use. No big-bang switch, no rewrite from scratch.
The same API serves the Android app, the admin panel and any AI assistant, through one MCP server with named tools.
A large model is the wrong tool for listening all day. A small one, trained for a single word, runs on the phone and costs nothing per hour.
Claude is the brain, a browser is the hands, a database is the memory. The same pattern, for every chore that repeats.
Built for businesses that run on software they cannot switch off
Back offices, shops, planning tools, portals, booking engines. Whatever it runs on, it earns money every day, and the hours around it can be automated.
Which task would you hand to an agent first?
Tell me what you are running and where the hours go. I reply within one working day with a first opinion, free.