Accounting support in a tax advisory firm
A tax advisory firm pre-processes receipts and booking proposals locally: documents are extracted, categorized and matched to the books — client data never leaves the building.
Built with: Dify, Docling
Use-case finder
Coming soon
The use-case finder will help you work out, in a couple of sentences, where local AI with the rzfz.ai Stack — the integrated open-source stack for local AI infrastructure — supports your business in concrete terms. You describe your business in one or two sentences, and the finder proposes three concrete use cases — with a clear rationale for why each one fits your operation.
We're building the finder right now, and we don't want to announce it with a fake chat interface. Until it's live, two proven paths will get you just as far — and a preview of what local AI can concretely do follows right below.
What we are building right now, for example
The finder is a work in progress — these are use cases we already deliver for customers today on the rzfz.ai Stack.
Support email classification for IT operations
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
Central RAG knowledge base for production control
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
24×7 dev agent raising test coverage
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
Local image analysis in patient care
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
Framework for digitalization consulting
A structured consulting framework guides digitalization projects: process discovery, assessment and prioritization are supported by local AI workflows.
Built with: Dify
Local coding with on-box models
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
Risk assessment of requirements
Requirements are assessed locally for business risk, failure probability and complexity — informing how intensively each requirement gets tested.
Built with: Dify, Open WebUI
Finding TARIC goods codes via RAG
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
Document extraction and redaction of sensitive data
Inbound customer documents are extracted locally and sensitive data is redacted automatically before further processing — built together with PSA, awarded the Constantinus Award 2026.
Built with: Docling, Presidio, Dify
Read the case study →