what you get
- RAG: answers over your documents with citations
- Document checks: contracts, charters, HR and construction paperwork
- Agents with tools, memory and a human approval gate
- Evals and release guards that block quality drops
- Local AI on your own hardware when data cannot leave
- Cost, latency and quality monitoring
work like this
- Three AI document-check bots for a law firm, scans included, RU and UZ (NDA)
- RAG Knowledge Agent: chunking, vector search, cited answers
- AI Eval Lab: prompt regression tests with CI gates
- Nur: Gemma 4 through Ollama, no cloud and no API keys
how it goes
- discover: One call, then a short written brief: who uses it, what done looks like, what can break.
- spec: A protocol before code: data, rules, acceptance criteria and test cases agreed up front.
- build: I direct AI coding agents and review every diff. Fast iterations, small PRs, nothing unreviewed.
- verify: Tests, evals and a reference to compare against. Results are reproducible.
- ship: Deploy on Vercel or Railway, add monitoring, hand over docs and a runbook.
questions
How do we agree on scope?
After a 20-minute call and a short written brief you get a fixed scope and a date, so the plan does not grow on its own.
How long does it take?
A bot or a site usually takes 1–2 weeks, an AI feature 2–4 weeks, a web app or MVP 4–8 weeks. You see a working version early and then every week.
Who owns the code?
You do. At handover you get the repository, documentation, a runbook and tests, deployed to your accounts.
Will you sign an NDA?
Yes. Most of my paid work is under NDA, which is why client names on this site are hidden.