Max Sushchuk at DOU Day 2026
Max Sushchuk AI Operations · Kyiv

I design how AI organisations operate.
First for myself. Then for clients.

The centre is my personal AI ops — a multi-agent workspace I built so I can think and ship at the pace this work requires. Around it: complete systems I shipped end-to-end for client orgs. The personal infrastructure is what makes the orbit possible.

personal AI ops Swarm workspace
AI-Ops kit
Content pipeline
News-digest swarm
AI Recruiter
Sales-intel agent
AI-Ops kit

A Claude Code skill catalogue with subagents that turns a multi-system operations investigation into a single conversation. Built solo in 4 days; 14 skills + 3 subagents in production, rolling out across the operations team.

highlights: skill catalogue · subagent fleet · meta-skill scaffolding · per-builder OAuth · structured audit trail · CI rule-promotion

Content pipeline

Turns a content brief into a published article, in 4 languages. Stages: normalize → validate → render → publish. 3–4 months of work; used daily by 2 writers.

highlights: normalize → validate → render → publish · 3 renderers · 12 rule docs · author profiles · drive/docs · translation glossaries

News-digest swarm

A multi-tenant runtime that runs many independent news-digest agents from one codebase. Each agent collects, ranks, and delivers a weekly digest to its team's chat channel. Three days of build; seven test runs to polish before regular delivery.

highlights: python pipeline · pgvector dedup · LLM ranking · chat delivery · ops channel · /metrics endpoint · scheduler · 159 tests

AI Recruiter

End-to-end recruitment automation, soup to nuts: a marketing landing page, a chat-app intake agent that interviews candidates, an admin SPA for recruiters, and a SQL backend tying it together. 195 automated tests cover behaviour. Currently in pre-launch.

highlights: landing page · chat-app intake · admin SPA · SQL backend · observability · questionnaire engine · vacancy matcher · outreach log

Sales-intel agent

A chat-triggered agent that finds B2B contact intelligence for a sales team. Salespeople ask in plain English; the agent returns enriched records via a spreadsheet. 7 months in production, ~1,000 records per week.

highlights: chat trigger · workflow runtime · operator-per-domain · dual-model fallback · spreadsheet delivery · scraper sub-workflow