AI-native senior full-stack engineer · available November 2026
Fifteen years of shipping software, nine in TypeScript, React and Node.js. I built agentic systems before they were fashionable and today an agent opens about a third of my team’s pull requests. If your roadmap still slips with Claude Code in the building, that gap is my job.
Available from November 2026 · Wrocław, Poland (CET), remote
The stack I ship with
Does this sound familiar?
Claude Code and Codex produce ten times the output and ten times the mess. Nobody owns the rules, the tests or the review. Every week adds velocity and debt in equal measure.
I write the rules the agents work under, put lint and test gates in CI, review what comes out and disclose what was AI-assisted. You keep the speed.
How I run agentsA demo became a product. No tests, no analytics, secrets in the repo, a deploy that only one laptop can run. Each new feature breaks two old ones.
A one-week audit with findings you can act on, then a rescue sprint: tests around the money paths first, then the three biggest risks, then a deploy anyone can run.
Rescue and take-overThe dashboard exists, the tracking plan does not. Leadership asks and engineering guesses. AI without analytics is running blind, only faster.
PostHog from day one: a tracking plan per feature, a first-party proxy so the data arrives, dashboards leadership reads without asking.
Measure what shipsCustomers ask for an MCP server, an API agents can call safely, an AI feature with a real evaluation loop. The team has the API and none of the rest.
An agent and MCP readiness audit, then the server: narrow tools, existing auth, adoption measured per client from the first merge.
Agent and MCP readinessHow we can work together
Scope first, then a number in writing. The call is free either way.
1 week
Your API, auth, tool surface, evaluation data and analytics, read by someone who has shipped this. You get a written report: what an agent could safely do today, what needs work, a plan with milestones.
3 to 6 weeks
One outcome, shipped and measured: an MCP server, an AI feature with an eval loop, a vibe-coded MVP made production-ready, a Next.js app that stops hurting.
2 to 3 days a week, 3 months minimum
Inside your team: architecture, code review, the rules for coding agents, hiring screens, the estimates. Your team keeps shipping, I keep the direction and the quality bar.
Services
Interfaces, tests and the dashboard that proves they work.
Live demo: editable component with Profiler →App Router done right, or an honest exit plan.
Live demo: waterfall vs stream timeline →Typed APIs, Postgres at scale, tests that encode security.
Live demo: JSON to TypeScript types →Browser and Node.js, with or without a framework, legacy included.
Live demo: the event loop, visualized →Workers, Durable Objects, R2, Workers AI, with cost caps.
Live demo: served from the edge, live →Upgrades with a safety net, migrations, GitHub Actions, legacy kept alive.
Live demo: dependency upgrade planner →Scope to production, solo or as fractional tech lead.
Live demo: estimate with an AI coefficient →From first commit to paying users: billing, tenants, stores.
Live demo: first four weeks planner →React Native, Electron, PWA, every store that matters.
Live demo: your device, probed live →IMAP clients, templates that survive Outlook, SPF, DKIM, DMARC, BIMI.
Live demo: check your domain’s email posture →Adoption plans, custom agents, MCP, skills and rules for coding agents.
Live demo: AI readiness scorecard →Agents in production: tools, MCP, evals, cost caps.
Live demo: ask my agent about me →Tracking plans, first-party proxy, dashboards leadership reads.
Live demo: live event feed of this page →Keep the old system alive, then move it without a rewrite.
Live demo: C# to TypeScript translator →Browser, desktop and mobile games, from the loop to the leaderboard.
Live demo: thirty seconds of arcade →How I work with AI
Mechanical checks over written guidelines: lint and test gates for security, API surface and CSP. The model suggests, the criteria decide.
About 30% of merged pull requests across two products in 2026 came from an agent. I reviewed about 85% of them. The responsibility stays with me.
Best-of-n, LLM-as-judge, scoring against fixtures. Many models compared across releases, swapped when the numbers say so.
AI-assisted work is labeled as such, to the team and to users where it matters. Agents are teammates, not ghostwriters.
Proof
Problem, what I did, result. Client names only where I am allowed to use them.
See also: SaaS & MVP · Mobile & desktop apps
See also: AI & agents · Full-stack & custom software
See also: AI & agents · PostHog & product analytics
One foot in the door
Two ways to see how I work before you commit to a sprint. Fixed scope, a number in writing after a short call.
I read the repo, CI, tests, security and the parts the team avoids. You get a written report with findings ranked by risk, a plan with milestones and a go or no-go you can defend. I have run this for a large software house before its clients saw the code.
Send me the diff that worries you. Within a few days you get line-level comments, the three things I would change first and whether I would merge it.
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
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
