DOBROVOLASergei Audzeichyk · AI implementation consultant and agentic workflow architect
Discuss a project

DOBROVOLA · Sergei Audzeichyk

AI implementation consultant and agentic workflow architect for business and knowledge-intensive processes.

Sergei Audzeichyk designs and implements AI systems for processes where data quality, verifiability, and human accountability matter. He combines business analysis, agentic system architecture, and evidence-aware knowledge work. At dobrovola.dev, he publishes methods, experiments, and open materials on practical AI implementation in organizations and professional workflows.

Explore the workWrite an email
01

Approach

AI implementation with a visible path to sources and human decisions.

The work starts with the workflow, data, and quality criteria—not a model choice. The result should retain intelligible sources, boundaries, and verification steps.

02

Selected work

Four published case studies

Pilot / Legal AI and Computational Law

NormaLab

Conventional legal search retrieves similar documents. NormaLab asks a different question: how did a specific rule operate across a body of judgments, where is practice stable, where does it diverge, and what supports each conclusion?

The public method exposes the path from question and corpus to citation, report, and evaluation verdict—even when the work is returned for revision.

My role

Data engineering · Agent systems · Reproducibility · Citation engine

Evidence

live demo · article

CASE / NORMALABcase-v1.1 →

Research / Open and Applied Research

BY Maps

BY Maps combines 129 years of demographic data, an interactive map, eleven research tracks, and three scenarios through 2075. It tests whether an engineer can enter a new field and publish work that a domain expert can reproduce, challenge, and recalculate.

The site combines a country-to-city atlas with eleven research tracks; every result leads back to data, code, and assumptions.

My role

Research framing · Data pipeline · Modelling · Visualisation

Evidence

live demo · repository

CASE / BY-MAPSresearch-v1.1 →

Prototype / Agentic Engineering

Academic Agent Workspace

An original course and protected environment where educators and researchers build an agent workspace through inspectable artifacts.

The result combines a public nine-session curriculum with a protected teaching space, a versioned material corpus, search, and course packages.

My role

Author and instructor · Curriculum design · Workspace architecture · Project mentoring

Evidence

live demo · live demo

CASE / ACADEMIC-AGENTcase-v1.1 →

Open source / Agentic Engineering

Dobrovola Codex TwinLoop

An open two-role workflow: specification → code → pull request → CI, with separated responsibilities and quality gates.

The repository demonstrates a controlled agent workflow rather than code generation in isolation.

My role

Workflow design · Specification · Quality gates · Open-source publication

Evidence

repository · article

CASE / TWINLOOPopen-v1.0 →
All work →
03

Writing

Methods, experiments, and open material

Law as a chain of events

An event model separates documents, facts, actions, and legal qualification instead of treating law as a flat collection of text fragments.

research essay

Open source as evidence of work

Public code can reveal process, tests, and decisions, but only scope and limitations make it interpretable as evidence.

engineering note
Read the writing →