Drop-in AI agents, QualityProfit baked in.
Production-grade AI agents for teams shipping software with Claude Code, Cursor or Copilot — each with QualityProfit's quality and observability layer wired in from day one. Built for insurance, financial services and government, where privacy, security and audit trails aren't optional.
Pre-order opens Q3 2026. Need a custom build instead? Paul takes a few Studio engagements per year.
Built for software teams where auditors care.
The agent catalog itself is stack-agnostic — it runs alongside whatever you ship. But we built it for one kind of customer: software teams in regulated domains where AI-assisted code shipping needs to be auditable, traceable and defensible. Insurance, financial services, government. The places where "we'll fix it next sprint" isn't an acceptable answer to a regulator.
DORA is here. So is the auditor.
Insurers, banks, payment platforms, asset managers. DORA, GDPR, internal audit, third-party ICT risk — your AI-augmented delivery pipeline has to be defensible to people who don't write code. The catalog gives you agents that gate, classify and log every change, with QualityProfit translating it all into financial-impact language for the people who sign your budget.
Auditable AI in delivery, by default.
Ministries, public-service implementers, government IT bodies. Algoritmeregister, AVG, BIO, NPR 5326, EU AI Act. The agents run inside your repo and your CI — not on a third-party cloud you don't control. Your AI-assisted delivery gets an evidence trail that survives an inspector and a change of administration, with privacy and data residency answered by architecture, not by paperwork.
Velocity is up. Quality signal isn't.
CTOs, VPs of Engineering, Heads of QA in regulated organisations. Your team shipped fast with AI coding agents — review queues are a swamp and your CFO is asking what you're getting for the cost. The catalog gives you agents that gate, route and report, with QualityProfit's executive dashboard underneath.
We don't sell to everyone.
You're shopping for a generic AI-agent vendor with no regulatory story. You want a one-off Cypress audit. You're a pure consumer-tech consumer-internet team where "move fast, break things" is still the operating model. The catalog isn't for you — and we'd rather tell you that now than discover it in week 6.
AI ships fast. Audit trails don't ship with it.
Your team adopted Claude Code, Cursor or Copilot. Velocity went up. But now you have review queues full of plausible-looking code no one really checked, tests that pass without exercising anything, and a creeping sense that your audit story is built on screenshots and hope.
In regulated industries, that gap isn't a productivity issue — it's a risk issue. DORA, the EU AI Act, NIS2, internal audit, your auditor's auditor: all of them are about to ask how AI-assisted shipping is controlled. Most engineering teams don't have a defensible answer.
We close that gap. Test architectures designed for AI extension. Custom agents that gate every push with evidence attached. A Language-First approach that makes specs, scenarios and tests legible to humans and LLMs — and to the auditor reading them next quarter.
The templates and writing we put in the open.
Top of funnel for the Studio. Fork the orchestration templates, read the field notes, get the Playbook when it lands.
orchestration-playwright-agents
Drop-in Claude Code orchestration template for Playwright E2E: master prompt as a skill, 8 specialised sub-agents, slash commands, starter e2e/ folder. Adapt it to your repo in a day.
View on GitHub →orchestration-cypress-agents
Sister template for Cypress: master prompt as a skill, 8 sub-agents, slash commands, starter cypress/ folder. Same pattern, framework-native.
View on GitHub →Field notes from AI-augmented engineering
Long-form on Language-First test design, in-repo subagents and the messy reality of shipping with LLMs. Monthly cadence resuming Q3 2026 — see the writing roadmap.
Read on Medium →The AI-Augmented E2E Playbook
15-page PDF: Language-First architecture, AGENTS.md scaffolds, Page Object pattern with AC/TS traceability, per-feature coverage matrix. Bundles three Medium pieces into one printable artifact.
Get notified →Production-ready AI agents — with audit trails included.
Drop-in agents for teams using Claude Code, Cursor, Copilot or similar — each with QualityProfit's quality and observability layer baked in by default. Distilled from real client work in insurance, financial services and government. Pre-order opens Q3 2026.
Compliance & risk · Shipping first
risk-classifier
Classifies every PR by business risk — auth, payments, PII, data migrations, external APIs — using project-specific rules + AST analysis. Routes to specialist reviewers and tunes gate strictness automatically.
compliance-guard
Checks code and tests against control frameworks — ISO/IEC 27001, GDPR, SOC2, DORA, NIS2, EU AI Act, WCAG. Flags violations as PR comments with the exact control IDs, so audit prep stops being archaeology.
Reliability & operations
incident-replay
Takes a production incident report, generates regression test(s) that would have caught it, and opens the PR. Closes the loop from outage to evidence — no more "we'll write the test next sprint."
perf-regression-detector
Runs benchmarks per commit — Web Vitals, p95 latencies, DB query plans. Fails the gate on regressions outside per-route tolerance bands. Tuned to your SLOs, not generic thresholds.
Quality & ROI
roi-tracker
Tags every gate run with a "value-prevented" estimate (cost-of-bug-in-prod × confidence). Aggregates monthly into an executive PDF your CFO will actually read.
flaky-quarantine
Detects flaky tests using rolling pass/fail history. Auto-quarantines after N flakes, opens a debugging issue with a templated checklist, removes the flake from the gate so the rest of CI stays green.
Orchestration
api-contract-guard
Detects breaking API changes between commits — REST, GraphQL, gRPC. Compares OpenAPI / SDL against the last green build, warns on backward-incompatible deltas, suggests a deprecation path.
agent-conductor
Orchestrates the open-source 8-agent template + your proprietary agents. Decides which run when, balances load, batches model calls, dedupes runs. The second-order agent that makes a 6-agent stack tractable.
What this looks like in practice.
From government rollouts to solo SaaS — with audit trails attached.
Language-First in gov.
Cypress + Playwright architecture
Test architecture across multiple government departments where specifications, scenarios and tests share one continuous human-readable layer. Presented at CypressConf 2024 — "Beyond the Battle: Empowering Test Automation with a Language-First Approach."
Architect for the long run.
Test Automation Architect
Cypress + Lit Elements test architecture with Cucumber traceability, integrated into Azure DevOps. Built to outlive me — handed back to the team.
Global rollout, audited.
QA Architect & Test Manager
Test management for a worldwide rollout under ISO 25010 / TMap discipline; earlier engagement covered Cypress / Angular / Docker on Azure DevOps.
Quality Framework rollout.
Quality Assurance Manager
TMMi-aligned Quality Framework on top of ISO/IEC 25010, embedded in delivery pipelines for a national utility.
Solo SaaS, four agents.
Founder · Full-stack with Claude Code
A customer-deployed dashboard that turns Jira / Azure DevOps / GitHub / GitLab signals into financial ROI for QA. Four in-repo subagents: release-reviewer, deploy-monitor, onboarding-smoke-tester, requirements-guard.
Their AI test stack, productized.
Architecture · Framework · Claude Code skill
Built an AI-augmented Playwright architecture, framework and reusable Claude Code skill for a Dutch digital agency — designed to drop into any current or future client engagement, not built for a single project. Codifies project structure, Page Object pattern, AC/TS traceability and per-feature coverage matrix. Proof that productized AI-testing assets work at agency scale — the same thesis the catalog rests on.
Your teams prevent millions in losses. Now prove it.
QualityProfit makes the invisible costs of software delivery visible, measurable and actionable. Connect Jira, Azure DevOps, GitHub or GitLab — get a Quality Cost Ledger, a Correlation Engine that traces causal chains, and executive dashboards that translate quality into financial impact. Built for the conversations regulated organisations are about to have with their auditors. The panel on the right mirrors the sample 250-engineer projection from qualityprofit.io.
- release-reviewer — gates pushes on risk patterns
- deploy-monitor — verifies container digests on the VPS
- onboarding-smoke-tester — walks the wizard end-to-end via the real API
- requirements-guard — reconciles spec against live code
Need something the catalog doesn't cover?
Paul takes a small number of custom Studio engagements per year for clients in insurance, financial services and government whose agent need doesn't fit a productized offering — or whose procurement reality requires a fixed-scope contract. Each is bundled with QualityProfit and starts with a free 30-minute scoping call. Standard DPA, contract templates, and DPIA support available — prices in EUR, USD/GBP equivalents on request.
What I bring into your repo.
Pragmatic, opinionated, and chosen for AI extension — not novelty.
15+ years across enterprise & government.
A selection — earlier roles span ING, SBB, Ministry of Foreign Affairs, ZLM, KPN and lecturing at The Hague University of Applied Sciences.
Pragmatic guides on Cypress, testing & automation.
On Medium since 2020, with 10+ deep-dives on Cypress patterns, ROI for testing, and test strategy. New AI-augmented engineering pieces landing on this site through 2026.
Pro-tip: stub the window object. A practical walkthrough for the multi-tab problem Cypress users hit constantly.
Cross-origin testing is finally there. What changed, what to watch for, and how to migrate your auth flows.
And why you should care. Where the lines are, why teams confuse them, and how to pick the right tool for the assertion.
On stage, on a podcast, in your team's Slack.
Cypress.io Ambassador, conference speaker, certified didactical trainer.
Cypress Ambassador
Active community work
Conference Speaker
CypressConf 2024 + 2025 workshops
Certified Trainer
Software testing & QA · Post-HBO didactical
Talks on YouTube
Recorded talks and workshops.
Cypress: The Bad Practices Workshop
Hands-on tour of the Cypress anti-patterns we keep meeting in real codebases — and how to refactor out of them. Co-presented with Frits van der Sloot.
Watch on YouTube →Beyond the Battle: Empowering Test Automation with a Language-First Approach
How specs, scenarios and tests can share one continuous human-readable layer — and why that shape makes AI extension tractable.
Watch on YouTube →Effective Test Automation Design
The architecture decisions that make a test suite outlive the team that wrote it — Page Objects, traceability, and the discipline behind a pyramid that holds.
Watch on YouTube →Got an AI rollout that's outpacing your audit trail?
Book a free 30-minute call. I'll listen, ask sharp questions, and tell you honestly whether I'm the right person for the job — or whether you'd be better served by someone else.