Mike Czerwinski

AgentOps. AI System Audit.

I audit memory, decisions, locks, and coherence in AI agent stacks. Twenty years building software, now applied to systems shipping before anyone understands them.

Talk to me → LinkedIn DM
01

What I do

Four engagements, in descending priority.

Audit AI agent systems

Memory architecture, decision coherence across sessions, lock semantics, source attribution, hallucination surface, two-register failure modes. One engagement currently in motion. Quietly.

Build agent infrastructure for regulated contexts

Typed memory with source attribution. Decision lifecycle (proposed, accepted, locked, defended against silent overwrite). Process threads. Cross-session distillation. Write-time invariants. Refusal as a first-class output.

Difficult second reader for AI product narratives

If the landing page is louder than the engineering, I notice. I tell you. Quietly.

Compliance audits, on request

EU AI Act Art. 50, DSA wave 2, GDPR DPIA, Directive 2024/1385, age-verification (UK OSA, EU AVMSD, DE JuSchG). The same map I run on my own company internally. Available when the engagement calls for it.

02

How I work

Operator diligence is the rare resource. Capability is cheap.

Five primitives I keep coming back to across every engagement. They are the parts most AI products skip until something breaks in production.

  • Auditable decisions with explicit lifecycle, not silent overwrites.
  • Defended locks on what must not move, enforced at admission, not at retrieval.
  • Source-attributed memory with per-atom provenance, not flat conversation history.
  • Write-time invariants that reject confident-but-unverified output before it propagates.
  • Refusal as first-class output. The model saying "I will not answer this" is a feature, not a failure mode.

I call this working frame agile4ai. More on it post by post on dev.to/jugeni.

03

Why now

Capability is no longer the bottleneck.

AI agents are shipping into production faster than anyone can understand the systems they run. The marketing layer ships in week one. The receipt under it ships never.

This used to be a hobby concern. It is becoming the operating reality across regulated industries, finance, security-sensitive consumer software, and any product that delegates real decisions to a model.

The bottleneck is the layer between the model and the consequences: who verifies what, when, and on what evidence. That layer needs engineering, not opinion pieces.

04

Receipts

Public work, built systems, peer convergence.

Published

Built

  • sentixx.net
    Polish simple joint-stock company. Content provenance and RegTech infrastructure (multi-tenant trust-and-safety engine).
  • jugeni
    Agent infrastructure: typed memory, decision lifecycle, process threads, write-time invariants. Open source.

Peer convergence

Public threads where the work intersects with other practitioners building in the same problem space. Examples available on request.

05

About

Twenty years building software.

Eleven years hands-on development across e-commerce, media, and consumer web (PHP, JAVA, node.js, Spring, MySQL, AWS).

Nine years as Scrum Master and Agile lead across banks (BNP Paribas, Citi), automotive R&D (FEV Polska, delivering for Deutsche Post StreetScooter electric fleet and Hochtief Germany), travel-tech (Sabre, in a SAFe environment).

Now founder of three product lanes under one obsession: making opaque AI legible enough to ship without lying to the user. Content provenance (sentixx.net), quantitative trading research (ziom), custom-tailored personal AI (jessi).

Based in Poland. Working in English and Polish.

06

Contact

Talk to me.

I read every message. I reply to the ones where the gap between what you have and what you need is engineering, not vibes.