One engineer, many agents.
I’m an AI/ML engineer, software engineer and tech lead — ten years of real-world projects, from ML systems to production backends. These days I build almost everything with AI agents, and I publish the whole process here.
What this is
Akribia Labs is my workshop, not an agency. The content flood around “building with AI” is hype-merchants on one side and doomers on the other; the honest middle — spoken by someone with production scars — is nearly empty. That’s the gap this publication fills: the good, the bad and the ugly of agentic engineering, as a literal taxonomy. Every build log carries a verdict, and every case study ends with one.
Nothing here is offered; everything is shown. If I claim a method works, there’s a PR behind the claim. If it didn’t work, that gets published too — the bad and the ugly pages exist because nobody selling something can afford to write them.
The method
The opposite of vibecoding. What survives review, in the order it happens:
- Spec before code. Every change starts as a written plan an agent (or I) can be held to — scope, contract, verification criteria.
- Adversarial review. Multiple reviewer agents, each briefed to refute the work and each other — not to agree. This has caught bugs I would have shipped.
- Contract-first codegen. One schema as the single source of truth, with every language binding generated from it, so interfaces can’t drift.
- Isolation. Parallel agent work happens in isolated worktrees; nothing lands unmerged, unreviewed, or untested.
- Verification before “done”. A change is finished when its behaviour is observed, not when the diff looks right.
The full method, applied end-to-end, is documented in the QuantScreen case study and taught in the course.
Why no face
The brand is the publication; the voice is the engineer. The work is public — the PRs, the failures, the numbers — and that’s where the credibility has to come from, not from a headshot. My legal name sits where German law requires it: the imprint.
On the bench
QuantScreen, my quant equity screener and the flagship case study. Mage Survivor, a bullet-heaven incremental RPG built with the same discipline. And the newsletter — AI & Tech, distilled into one considered digest.