NedDev®
NL Get in touch
Home Work
Services
SaaS developmentAI developmentAPI developmentMobile app developmentGoogle Ads managementHeadless ShopifyLaravel developmentNext.js developmentReact developmentTypeScript engineeringUI/UX designSEO & AEOEcommerce development
Solutions
AI solutionsB2B platformsE-commerceHospitalityLead generationLogisticsEducationProcess automationSaaS platformsStartup MVPReal estateHealthcare
Industries
LegalHealthcareReal estateFinanceHospitality
Regions
The HagueRotterdamAmsterdamUtrechtEindhovenAlmereBredaArnhemNijmegenTilburgEnschedeGroningenLeidenDelftZoetermeerDen Bosch
Studio
AboutProcessLabBlogContact
STUDIO Nº 04 · NEDDEV ATELIER AI SAAS · DIGITAL EMPLOYEE · 2026
CASE · 02 OF 32

Cor®

The universal AI employee. Multi-tenant platform with voice + RAG + Nango. Our own product.

Cor® AI digital employee SaaS platform
In short

Cor is the universal AI employee: a multi-tenant SaaS platform that gives each customer a digital worker with voice, RAG knowledge and Nango integrations. A NedDev in-house product, built to take repetitive work off teams and give every organization its own securely isolated AI colleague.

Next.js✦React 19✦TypeScript✦Laravel 12✦Tailwind CSS✦Filament✦Node.js✦Python✦PostgreSQL✦Redis✦Supabase✦Prisma✦Shopify✦Stripe✦Mollie✦GraphQL✦tRPC✦React Native✦OpenAI✦Anthropic Claude✦LangChain✦RAG✦Computer Vision✦Pinecone✦AWS✦Cloudflare✦Vercel✦Docker✦Kubernetes✦Terraform✦Three.js✦WebGL✦GSAP✦Framer Motion✦Playwright✦Vitest✦Next.js✦React 19✦TypeScript✦Laravel 12✦Tailwind CSS✦Filament✦Node.js✦Python✦PostgreSQL✦Redis✦Supabase✦Prisma✦Shopify✦Stripe✦Mollie✦GraphQL✦tRPC✦React Native✦OpenAI✦Anthropic Claude✦LangChain✦RAG✦Computer Vision✦Pinecone✦AWS✦Cloudflare✦Vercel✦Docker✦Kubernetes✦Terraform✦Three.js✦WebGL✦GSAP✦Framer Motion✦Playwright✦Vitest✦
OWN IP · STUDIO OUTPUT

Not just client work. Our own products too.

OPEN SOURCE · STUDIO LAB ↗

NedDev WRK®

Our internal stack packages for multi-tenant SaaS. A Laravel + Filament starter, an audit-trail engine, and a tenant-impersonation package that runs across 12 clients.

8 PACKAGES · 2.4K STARS EDITORIAL · LONG-FORM ↗

NedDev Journal©

What we write down as we learn it. Case studies, technical write-ups, design decisions. No content marketing, just real knowledge.

42 ESSAYS · MONTHLY RESEARCH · AI EXPERIMENTS ↗

NedDev Lab™

Side projects and R&D. Voice-agent prototypes, RAG pipelines, AI knowledge-graph experiments. Some become products. The rest teach us something.

14 EXPERIMENTS · LIVE DEMOS
— CHALLENGE

The challenge at Cor®.

The market for AI employees is dominated by US players like Sierra and Decagon. The Dutch SME market lacks a serious alternative that genuinely masters the language, handles phone calls, and keeps data inside the EU. NedDev set out to build that alternative as its own product: Cor, a universal AI digital employee.

The core brief was deliberate: not tied to one sector, but configurable per client through a multi-tenant platform. Cor had to combine voice, knowledge drawn from a client's own documents, and connections to existing systems, all while strictly meeting GDPR and the EU AI Act. Tenants could never be allowed to see one another's data.

— APPROACH

Our approach.

After sixteen research streams, NedDev settled on a fully EU-hosted stack built on the familiar Laravel 12 and Filament foundation. Voice runs through Pipecat Cloud with Gemini Live, and knowledge through an in-house RAG layer on Postgres with pgvector. For the hundreds of integrations, NedDev chose Nango self-hosted over pricier alternatives.

Isolation is structural: each tenant gets its own Postgres schema and its own vector namespace with a tenant filter. The EU AI Act disclosure is hardcoded into every conversation from day one. The method was disciplined: research, plan, one-shot build, always on DEV first and only then to production.

— OUTCOME

What it delivered.

In its first session Cor went from zero to a live deployment in a single day, with seventeen commits and seventy-two passing tests. The admin panel, the Cor Sandbox, and the knowledge upload are running, while the control plane plus the TEI and Qdrant services run 24/7 under systemd and Docker.

It is proven end to end: asked for an inspection price, Cor answers correctly with the required disclosure, while a question outside its domain is politely refused. Multi-tenant isolation holds across both Postgres and the vector store. The product itself targets a thousand euros per month per client, with a founding rate for the first five.

YOUR NEXT PROJECT

Ready for your next build.

Book an intro → Direct line to the founder · M. Tufan