Playwright + CI · AI agent evals · Bucharest, EU time zone

Test suites that run in minutes and don't lie.

Playwright and CI engineering for SaaS teams of 20–150 engineers, plus evals for AI agents. Every engagement starts with a paid one-week audit.

38caught before prod
6hfind → shipped fix

Illustrative run, not live data

Three things we do.

Testing & QA

Playwright test automation and CI you can trust. Cypress or Selenium to Playwright migrations, flaky-test cleanup, GitHub Actions and Azure DevOps pipelines, self-hosted runners, fractional QA lead. Starts with a one-week audit.

Read more

AI agent testing

Evals for agents and RAG with promptfoo, Ragas, DeepEval and LangSmith. Prompt-injection and safety testing. Eval suites that gate CI, so a regression fails the build before it reaches a user.

Read more

Development

Web apps and APIs in React/Next.js, Node/NestJS and Python. AI agents and workflow automation. Delivered with the test suite, not after it.

Read more
Proof

Claimed is cheap. Here's what shipped.

Three engagements, anonymized. What broke, what changed.

AI support chatbot · LLM behavior

The assistant regressed on every prompt change, with nothing to catch it.

no eval coveragegraded golden set on CI
Read the full story
No-code e-commerce shop · checkout

Checkout silently dropped orders under a race condition no test covered.

orders lost, unnoticedrace fixed · regression test gating checkout
Read the full story
Clinic booking app · scheduling

A timezone bug double-booked slots and overran the calendar.

double-booked slotscorrect across time zones · covered by tests
Read the full story
All case studies
38bugs caught before they reached production
6haverage time from find to shipped fix
0missed launches on our watch
1 day+to ship a small feature — bigger scopes scale up

Illustrative example, not live data

Cristian-Robert Iosef

Founder · QA and CI engineer

Eleven years in test automation and CI. Playwright, TypeScript, GitHub Actions, Azure DevOps.

Stack
PlaywrightTypeScriptGitHub ActionsAzure DevOpsDockerKubernetespromptfooRagasDeepEvalLangSmith
FAQ

The questions you'd ask on the call.

Why is the audit paid?

It is a week of senior engineering time and it produces a report you keep. An unpaid audit is a sales call with a checklist.

What does "from" mean?

The price for the smallest scope we accept. The audit fixes the real scope and the proposal states a fixed price for it.

Do you work in our time zone and under NDA?

Bucharest is UTC+2, one to two hours ahead of most EU teams, overlapping the US East Coast morning. NDA before anything is shared.

Who does the work?

The engineer named in the proposal. For audits, Foundation and migrations that is the founder. No senior-to-junior swap after signing.

Can you test an agent we built elsewhere?

Yes. The eval suite is written against the agent's API or UI. Your code does not have to change.

Next step

Book a 30-minute discovery call.

Tell us about the suite and the CI. We say whether an audit makes sense and what it would cover.