Vienna, Austria
I've spent the last two decades building TEAMBOX, the ERP platform for service providers that's become the PSA market leader in DACH — starting as one of its earliest developers, now running enterprise integrations, CI/CD, and the team behind it. My current focus is agentic engineering: building AI-driven development workflows into a live, twenty-year-old codebase without breaking it.
Work Highlights · June 18 – July 9, 2026
Updated roughly every three weeks, straight from the actual work — not a highlight reel.
Featured build
Most "AI wrote some code" stories stop at code review. This one runs unattended against production. Once a week, a Claude Code command connects to our log aggregator, pulls the highest-volume error patterns, and works through them like a careful on-call engineer would — not a script that just counts lines.
The hard part wasn't the log analysis — it was making it deterministic. The same command, run by a different AI session or a different teammate months from now, has to produce the identical dashboard from identical inputs. That meant writing out the exact fingerprint algorithm, the exact API quirks, and the exact layout rules as if onboarding a new engineer with zero context, because in practice, that's exactly what it is.
Featured build
Sprint retros used to run on gut feel and whichever ticket someone happened to remember. This is a Claude Code command that turns raw ticket history into a dashboard the team actually opens — not because it's flashy, but because two rounds of "that number's wrong" feedback got taken seriously and fixed instead of explained away.
Some of it was about restraint, not features: a stacked-bar chart got built, tested against real data, and then dropped because its rounded segments visually misrepresented small proportions. The donut chart stayed; the flashier option didn't make the cut.
Stood up our first real end-to-end suite against a legacy ExtJS/React hybrid frontend — and it caught a genuine race condition (a stale setTimeout navigating an unmounted modal) that intermittently left users staring at an invisible editor. Now it's a tracked bug instead of an occasional complaint.
Evaluated a third-party AI agent development platform against our actual CI and security requirements, not a sandbox demo — then wrote up a structured, specific feedback doc (missing ticketing-system adapter, a false-positive test gate, settings pollution) instead of a vague verdict. Picked up hardened CI along the way: dependency review, security scanning, an IAM fix — independent of what we decide about the platform.
Shipped a broad exception-handling audit across ~60 files, watched it get reverted the same day during a rebase (and take unrelated infra code down with it), tracked down and restored the collateral damage, and kept the design as an architecture decision record instead of forcing the merge. Sometimes the honest outcome is "documented, not yet landed."
Several enterprise clients lost document upload at once via an OCR integration. Root cause was two compounding issues — a missing config guard and a subtle typo in an API-token check — found and fixed same day, with structured error logging added so telemetry catches the next one before four separate client reports do.
Kept a multi-week Docker infrastructure migration merging cleanly into an active release branch — recurring conflict resolution, a CI pipeline fix, release prep. Small diffs, but this is the work that decides whether an infra migration ships quietly or breaks the release train.
Personal AI Research · Proof of Concept, July 2026
Built in my own time in Google AI Studio, not on the clock — a way to stress-test what Gemini can actually do on a real, messy problem instead of a toy demo.
Personal AI Research
A maps-based dashboard that monitors global conflict events close to real time. It takes open-source reports — social posts, wire dispatches, radio transcripts — in whatever language they were written, and turns them into structured, geolocated, credibility-scored events a researcher can actually use.
This is a personal research prototype, not a production intelligence product — the live feed uses Gemini search grounding against open sources, with a documented offline fallback dataset for when that harvest fails. Built end-to-end (React, Express, Gemini API) in Google AI Studio and deployed to Cloud Run.
View live app →Year in Review · July 2025 – July 2026
A thematic look back, not a changelog — roughly 150 shipped commits across ~110 tickets.
The biggest shift this year: bringing AI-driven development into a twenty-year-old codebase without treating it as a toy. Built and hardened internal Claude Code tooling — a sprint-KPI dashboard, a deterministic log-triage command, the first real end-to-end test suite — and ran a structured evaluation of a third-party agentic-engineering platform against our actual CI and security needs rather than a sandbox demo. Commit volume roughly tripled from spring to summer as the workflows matured.
Investigated a session-backend redesign (Redis-backed, documented in its own architecture decision record) and landed a change that cut session payload dramatically — then caught a Control-state edge case in review and reverted that specific piece the same day rather than let it ride. Followed up with safer, incremental steps: monitoring, a config switch, sampling-based measurement instead of a per-request check. The win that shipped was smaller than the one that didn't — that's the honest version.
Ran a systematic exception-handling audit across roughly 60 files spanning auth, transport, sync, and file storage, and wrote it up as an architecture decision record on how permission failures should signal denial instead of getting silently swallowed. Part of the audit shipped and was reverted the same day during a rebase; the design stayed as documentation rather than forcing a merge that wasn't ready.
A multi-week Docker migration kept shipping cleanly against an actively-changing release branch through dozens of small conflict-resolution and pipeline fixes. Alongside it: CI hardening (dependency review, security scanning, tightened permissions) that came out of the platform evaluation but benefits every pipeline regardless of what we decide about that vendor.
Same-day fixes for production issues hitting enterprise clients directly — a multi-client OCR outage traced to a config gap and a one-character typo, a Microsoft 365 integration display bug — plus the ordinary, constant work of DATEV/Abacus/BMD accounting integrations, SSO/LDAP, and e-invoicing that a 300+ customer ERP platform runs on every day.