AI in your company, with receipts
I build agentic systems in production since 2024, without a framework tax: tools, evaluation loops, cost caps, MCP servers people actually use. In 2026 an agent opened about 30% of my team’s merged pull requests under rules I wrote. I can take your company from “we tried ChatGPT” to one workflow that runs on its own and gets measured. Score your readiness below in two minutes.
Available from November 2026 · Wrocław, Poland (CET), remote
Most AI pilots die because nobody picked the workflow, the owner and the metric before the demo. I start with a map of your processes, choose one with a clear number attached, and ship that one to production before touching the next.
No LangChain. Tools with narrow scopes, an evaluation loop with LLM-as-judge against fixtures, a cost cap in a Durable Object, models compared across releases and swapped when the numbers say so. My content platform published thousands of articles and a catalog of 10,000+ programs, ~97% automatically, on exactly that design.
CLAUDE.md and AGENTS.md that agents cannot skip, skills for the repeating work, hooks and lint gates in CI, a human review on every PR, AI-assisted content disclosed. That is how one product went to ~40× more commits year over year without the quality dropping.
An MCP server with narrow tools on top of your existing auth, adoption measured per client from the first merge, a bot-protection rule that would have blocked every agent found the same day because the dashboard showed it. If ChatGPT and Claude users want to talk to your product, this is the work.
Ways to work together
Scope first, then a number in writing. The call is free either way.
1 week
Your processes, data, API, security and team, read by someone who has shipped this. A written report: which workflow goes first, what an agent can safely do today, what has to change, a plan with milestones.
Book a free call →4 to 6 weeks
A single outcome in production: a support triage agent, a content pipeline, an MCP server for your product, a coding-agent setup for the team. Measured from the first day, handed over with the rules and the dashboard.
Book a free call →workshop + 4 weeks
A hands-on workshop, then rules, skills and review gates for Claude Code and Codex in your repos, then four weeks of pairing. The team keeps the speed and loses the mess.
Book a free call →2 to 3 days a week
Inside your team for a quarter or two: the roadmap for AI features, vendor and model choices, evals, costs, security reviews, hiring screens. Your people ship, I keep the quality bar.
Book a free call →Proof
Problem, what I did, result. Client names only where I am allowed to use them.
See also: AI & agents · Full-stack & custom software
See also: AI & agents · PostHog & product analytics
See also: AI & agents
Live demo
Twelve questions across six areas: data and APIs, process ownership, measurement, security, evaluation, team skills. You get a score per area, a verdict and a sketch of the first thirty days built from your two weakest areas. Everything runs in your browser.
Demo loading…
Copy the result as Markdown and bring it to the call. It becomes the agenda.
How it works
You describe the product and the problem. I ask the questions I would ask on day one. If I am not the right person, I say so and point you to someone who is.
A short written plan follows: what we build first, what we measure, how we work together and what it costs. No slide deck.
The first slice ships in the first week: deployed, measured, reviewable. From there the work is paced by what the numbers say.
Fit check
Working style
Claude Code and Codex work on main with hooks, lint and test gates. The model suggests, the criteria decide. Every PR gets a human review and AI-assisted content is disclosed.
Hundreds of pull requests reviewed. I review for the product and its reasons. The code comes second.
PostHog in every project from day one. A tracking plan per feature and dashboards leadership actually reads.
FAQ
A free 30-minute call. You bring the problem, I bring questions. No prices on this page because scope comes first.
If I am the wrong person I will say so on the call and point you to someone better.
After you book: a calendar invite, then the call. Nothing else to fill in.
Available from November 2026 · B2B contract or employment · Wrocław, Poland (CET), remote
