Skip to main content
Selected work

Work

Products, systems, and experiments built around real operational problems.

01 Operational accounting

K-Ledger

A focused operational accounting system built from the needs of a real operating business.

IN DEVELOPMENT

Problem

Operational accounting information can become fragmented across spreadsheets, receipts, messaging, inventory records, receivables, payables, and cash-flow tracking.

Context

K-Ledger originated from practical needs around Kovaa, a real B2B operating business used as a proving ground for internal systems.

System

Current scope is centered on operational accounting and evidence, including receivables/payables, inventory-related visibility, and cash-flow awareness.

Design decision

K-Ledger is intentionally not positioned as a generic full ERP. Tax accounting remains a distinct concern; the system is oriented toward operational clarity and human review.

Current scope

Scope currently being built.

  • Receivables and payables Obligations tracked back to the source invoice.
  • Inventory visibility Stock movement read against working capital.
  • Evidence Receipts and documents attached to line items for human review.
  • Cash flow A forward view of liquidity built from actual operational state.

Domain

AccountingOperationsEvidenceCash flow
02 AI-assisted software development

Prokron

One project. Shared understanding.

R&D

Problem

Complex AI-assisted work loses continuity whenever the model, session, or person changes. Decisions, intent, and current position have to be reconstructed from chat logs, and a newcomer has to read implementation code to learn what the project is.

Context

Born from continuous daily development with generative coding agents and multi-session project lifecycles. Carried here under the working name Handoff until September 2026, and now developed in public.

System

Two entry modes: a new project derives its first tasks and decisions from its specification, while an existing one starts empty and records from the current session forward rather than inventing a history. Work then runs one task at a time — resume, work, decide, checkpoint. Installation is a single shell command, and the workflows are portable Markdown, so Claude Code, Codex, OpenCode, and any agent that reads an instructions file follow the same agreement.

Design decision

Prokron is records and workflow, not a runtime — Markdown files, agent instructions, and portable command prompts, with Git keeping file history. Completion and validation stay separate: a task is done when its acceptance evidence exists, and its validation is recorded as untested, synthetic, AI-reviewed, or human-verified, which only a named human may set. A changed decision is superseded by a new record; earlier ones are never rewritten.

Current scope

Working concepts under active research.

  • Living chronicle Project truth kept in the repository, next to the code it explains.
  • Two entry modes A new project starts from its specification; an existing one starts empty and records forward.
  • One task at a time A single declared intent, with its owner, acceptance condition, and evidence.
  • Decision lineage Why the project has its current shape, with superseded choices left intact.
  • Checkpoint discipline The chronicle is written before a context, quota, or session limit ends the work, not after.

Source

qomerovn/prokron

Apache-2.0

Domain

Open sourceChronicleContinuityAI workflows
03 Legal knowledge work

LeviDraft

A structured environment for bilingual legal drafting and review.

EXPLORATION

Problem

Bilingual legal drafting is not simply a translation problem. Source provenance, legacy language, drafting choices, review, and reconciliation all matter.

Context

Originates from real bilingual commercial and regulatory contract workflows in Vietnam.

System

Current exploration includes provenance tracking, legacy bilingual mining, structured drafting workflows, reviewer reconciliation, and evaluation/reward mechanisms.

Design decision

Do not position LeviDraft as “a better translator”. The product thesis is a specialized legal drafting and review environment.

Current scope

Concepts under exploration. Not yet built.

  • Provenance Tracing a clause back to the authority it came from.
  • Bilingual mining Surfacing legacy precedent across Vietnamese and English.
  • Reviewer reconciliation Structured resolution where two reviewers disagree.
  • Drafting environment A workspace built for clause precision rather than generic generation.

Domain

Legal draftingBilingual workflowProvenanceReview

We prefer systems that emerge from real constraints over technology built in search of a problem.