Case studies

Selected systems built for real operational work.

AI infrastructure, GenAI agents, CRM, booking, and logistics products with production-facing workflows and room to scale.

5 case studies / llm infrastructure / ai booking / operations crm / logistics

Case study

Selected build

Forge

Provider-agnostic system for running LLM batch and realtime jobs across OpenAI and Anthropic, with automatic retries and crash recovery.

~40/s
jobs per replica: ~50%
lower token cost: 2
LLM providers

Built with Node.js / TypeScript / PostgreSQL

View case

Holocomm — Multichannel AI Booking Agent

Case study

Selected build

Holocomm — Multichannel AI Booking Agent

AI booking agent that turns customer chats across WhatsApp, Telegram, Instagram, and more — via Zernio's unified messaging API — into structured bookings, confirmations, and operational follow-up.

~70%
turns with zero LLM calls: ~284K
lines of code: 8,700
test & eval cases

Built with NestJS / Redis / Next.js

View case

Case study

Selected build

Omni AI Integration Architecture

AI-augmented maritime CRM architecture for classification, entity extraction, prompt-action workflows, and operational automation.

~3,000
platform users: 4.5★
mobile app rating: 88%
AI-pipeline bugs landed

Built with React / TypeScript / Node.js

View case

Case study

Selected build

Apollon CRM

Full-stack CRM for pet boarding teams with room scheduling, client records, booking management, and financial reporting.

~€794K
transactions tracked: 784
clients: 73
boarding rooms

Built with React / TypeScript / Tailwind CSS

View case

Case study

Selected build

Fotokiklosi

End-to-end waste management platform coordinating collection points, routes, material handling, and internal reporting across Greece.

~20,000
collection points tracked: 3
organizations in production: EU
waste-tracking compliance

Built with React / TypeScript

View case

Each case focuses on the same thing: software that helps teams run operations without adding noise.