I build the parts of a company that don't go home at night.
Some run for clients, some run my own week. Either way, the best hour I get is the one where you explain a problem I have not seen before.
Write about what is not working, and we'll go looking for the sore spots and the growth areas together. More on that.
A Claude Code skill catalogue with subagents that turns a multi-system operations investigation into a single conversation. Built solo in about three weeks; 15 skills and 3 subagents, shipped to the operations team.
skill catalogue · subagent fleet · meta-skill scaffolding · per-builder OAuth · structured audit trail · CI rule-promotion
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.
normalize → validate → render → publish · 3 renderers · 12 rule docs · author profiles · drive/docs · translation glossaries
Every morning from 05:00 UTC the radar reads the whole market a B2B company sells into – 74 sources, its own customers beside tenders, regulators, competitors, research and the trade press of every industry it serves – weighs each signal against its own history and has a tray of opportunity cards ready before the working day starts.
74 sources · 9,114 records · ~1,500 analyst-hours of reading · every signal a rate against its own history · UNBASELINED, never NEW · two-witness rule · frozen evidence · three judges in shadow · a person presses send
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. Live in production, rebuilt so that every claim the agent makes is verified against tool evidence. 1,190 automated tests cover behaviour.
landing page · chat-app intake · evidence-verified intents · code-owned intake ladder · offline vacancy index · prompt-cache shim · persona regression harness · recruiter admin
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.
chat trigger · workflow runtime · operator-per-domain · dual-model fallback · spreadsheet delivery · scraper sub-workflow
A closed growth loop run by three agents and one operating surface: the first finds where AI answer engines cite a competitor instead of you, the second drafts the page fix, the third measures whether the citation came back – and feeds that into the next draft.
B2C software · answer-engine optimisation · propose → ship → measure → feed back
A typing trainer for reading foreign-language literature – type real stories at your level, in the alphabet you are trying to make automatic. Built and operated solo: 68 public-domain stories, each with three graded retellings glossed sentence-by-sentence into seven more languages.
own product · 68-story corpus · 8 languages · 3 CEFR levels · sentence-aligned gloss · national keyboard layouts · ambient beds
-
Swarm workspace
My personal multi-agent workspace – the operational foundation everything else runs on. A long-context AI agent as operating partner against a version-controlled homelab-ops repo; a hardened bastion as the blast-radius boundary; the rails the proactive-AIOps turn will run on.
-
AI-Ops kit
A Claude Code skill catalogue with subagents that turns a multi-system operations investigation into a single conversation. Built solo in about three weeks; 15 skills and 3 subagents, shipped to the operations team.
-
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.
-
Opportunity radar
Every morning from 05:00 UTC the radar reads the whole market a B2B company sells into – 74 sources, its own customers beside tenders, regulators, competitors, research and the trade press of every industry it serves – weighs each signal against its own history and has a tray of opportunity cards ready before the working day starts.
-
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. Live in production, rebuilt so that every claim the agent makes is verified against tool evidence. 1,190 automated tests cover behaviour.
-
Content operator
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.
-
Krapka
A typing trainer for reading foreign-language literature – type real stories at your level, in the alphabet you are trying to make automatic. Built and operated solo: 68 public-domain stories, each with three graded retellings glossed sentence-by-sentence into seven more languages.
-
Growth hacker
A closed growth loop run by three agents and one operating surface: the first finds where AI answer engines cite a competitor instead of you, the second drafts the page fix, the third measures whether the citation came back – and feeds that into the next draft.
what I’m into right now
- RevOps and DevOps – the two places where AI either touches revenue or holds the infrastructure up, and usually both at once.
- n8n automations with data security designed into the build rather than reviewed at the end of it.
- Krapka, my own product – a typing trainer for reading foreign-language literature.
- Ukrainian-language products, where the model performs worse than it does in English and has to be brought up to a working standard anyway.
where this is
- ✓6 client systems with case pages, at /cases. Each one is the same world you just saw in orbit, seen up close – the newest is Opportunity radar for a B2B product team.
- ✓My own product – Krapka, a typing trainer for reading foreign-language literature. The one thing here I can name directly.
- ✓The sun – /cases/swarm-workspace. The personal AI ops the rest of the orbit runs on top of.
- ✓A writing surface at /writing. The newest piece: Every fix was real, and the game kept dropping.