From your first use case to a proven reference: real-world use cases, an AI-assisted finder for your own situation, and real case studies as proof.
How the integrated rzfz.ai stack solves real problems — from practice, reproducible. Filter by industry.
Tax advisory
A tax advisory firm used to validate personnel provisions, revenue and inventory values by hand across PDFs, lists and account statements — days of manual work in peak season. Today a local workflow does the matching and prepares the notes to the financial statements in structured form: a well-founded basis of argument for upcoming tax audits, with data sovereignty staying entirely within the firm.
IT services
An IT service provider serving many SMBs received hundreds of support and log emails every day — sorting them by hand in the inbox was barely feasible. Today an unsorted flood becomes a prioritized list the support team can focus on, with classification running entirely locally.
Foreign trade / customs
In foreign trade, every good needed the right TARIC goods code from an extensive, nested nomenclature — a slow, manual search that took real experience. Today, the right codes are found in seconds, and the classification work stays entirely local.
Describe your business in one or two sentences, and the finder proposes three concrete use cases for where local AI with the rzfz.ai Stack — the integrated open-source stack for local AI infrastructure — supports your business, each with matching modules and a first step.
Your Box is thinking — local inference takes a moment…
A tax advisory firm automates the validation of personnel provisions, revenue and inventory values through intelligent data matching across PDFs, lists and account statements. The notes to the financial statements are prepared in structured form as well — for maximum efficiency and a well-founded basis of argument in upcoming tax audits.
Built with: Dify, Docling, GPUStack + llama.cpp
See details →An IT service provider serving many SMBs receives hundreds of log and support emails daily. A local workflow classifies them, separates noise from real incidents and prioritizes what a human needs to see.
Built with: Dify, GPUStack + llama.cpp
See details →A production-control company consolidates internal knowledge — manuals, incident history, process docs — into one central, local knowledge base that staff query via chat.
Built with: Open WebUI, Cognee, GPUStack + llama.cpp
See details →A local coding agent works around the clock on the in-house repository: writing unit tests, steadily raising coverage and opening merge requests — with no code ever leaving the infrastructure.
Built with: Codex, OpenCode, gsd-pi, Gitea
See details →Patient data processing with local vision models: disease symptoms are detected on photos directly on site — sensitive health data stays entirely within the facility.
Built with: GPUStack + llama.cpp, Presidio
See details →A structured consulting framework guides digitalization projects: process discovery, assessment and prioritization are supported by local AI workflows.
Built with: Dify, GPUStack + llama.cpp
See details →Developers use coding models directly on their own hardware — completion, reviews and refactorings without external API keys and without code leaving the premises.
Built with: Codex, OpenCode, gsd-pi, Open WebUI
See details →Requirements are assessed locally for business risk, failure probability and complexity — informing how intensively each requirement gets tested.
Built with: Dify, Open WebUI, GPUStack + llama.cpp
See details →The TARIC database as a local RAG: matching import/export goods codes are found from a plain description of the goods — replacing tedious manual search through the nomenclature.
Built with: Open WebUI, LightRAG, GPUStack + llama.cpp
See details →Inbound customer documents are extracted locally and sensitive data is redacted automatically before further processing — built on the rzfz.ai Stack, awarded the Constantinus Award 2026.
Built with: Docling, Presidio, Dify
Read the case study →A selection of the projects we've delivered over the last few months — anonymized where the customer prefers it, named where that's been agreed.
May we feature your rzfz.ai story too? Do get in touch → Contact
Services
Incoming customer documents are read locally and sensitive data is automatically redacted — built on the rzfz.ai Stack. The project won the Constantinus Award 2026.