Skip to content
AssessmentDE

AI Software Engineering

AI makes it fast. Experience makes it right.

Twenty years of real-time and AI systems, now combined with agentic AI development: the result is software that runs reliably — from a small automation task to a full customer portal.

Request a free initial assessmentReply within 2 business days
The tool is new. The craft is not.

Systems I helped build have run in automotive and medical-device manufacturing, at international live sports events, and in camera networks on three continents.

ENGILO in four answers

01What is it about?
Tailor-made software and AI solutions for small and medium-sized businesses — from a small automation task to a full customer portal. At a fixed price, and in the end the system belongs to you.
02Why now?
Agentic AI development has drastically lowered the cost of custom software — what used to take an agency budget is now within reach for any SMB. But the tool is new, the craft is not: speed without experience produces throwaway prototypes.
03What makes it special?
Twenty years of real-time and AI systems, combined with agentic development — plus the ownership model: fixed price, code and server belong to you, no subscription, no lock-in. And no project is too small.
04What happens next?
Tell me about one process that costs you time every week. The free initial assessment gives you an honest answer on whether it's worth it.

Request a free initial assessment

Case studies

Real projects first, prototypes and own developments after — every case carries its label.

01An AI assistant that never leaks company dataClient projectShow details +
Starting point
An online community received the same questions from its users every day. A cloud chatbot was out of the question: the data was sensitive and had to stay in-house — and nobody wanted recurring subscription costs either.
Task
An assistant that answers questions exclusively from the company's own knowledge — and lets an employee take over at any time when a conversation gets personal.
Solution
An AI assistant on the company's own server: it answers only from their own documents and never makes things up. One installation serves several clients, cleanly separated. Employees see every conversation and can take over. Connected to three channels: Telegram, team chat and the community app. Data protection built in from the start, including user consent.
Result
In production since August 2026. No document leaves the server. First client live, final polish under way.
Stack
Python · FastAPI · PostgreSQL + pgvector · Ollama · Docker
  • 3 channels
  • 1 installation, several clients
  • 0 documents leave the house
02Legacy software secured — during live operationClient projectShow details +
Starting point
Two connected applications from 2010, in daily use for years — but with security at yesterday's standard: vulnerable password storage, credentials in the source code, and no reliable way to ship a new version.
Task
Secure them without interrupting daily operations — and give an honest number for what a thorough rebuild would cost.
Solution
First a complete inventory: 22 vulnerabilities, sorted by urgency. Then the critical ones fixed — secure password storage (migrated invisibly for users), protection against automated attacks, credentials removed from the source code. Plus an automated safety net of tests and a deployment that is reproducible at the push of a button.
Result
Both applications have been running secured with the real production data since August 2026. The further rebuild is priced — the client decides at their own pace.
Stack
Java EE · MariaDB · Docker · GitLab CI/CD

Project ongoing; only completed work is mentioned.

  • 22 findings fixed
  • password protection modernised
  • 644 tests, 86% coverage
  • push-button deployment
03Website relaunch in four languages for an international advisory firmClient projectShow details +
Starting point
The old website came from a site builder, existed only in English, and loaded its images from third-party servers — neither professional nor privacy-friendly for an international wealth advisory.
Task
A multilingual website that actively wins clients: prospects request a whitepaper and land automatically in the sales system.
Solution
New website in English, German, Spanish and Chinese — all content and media on their own server, legal texts in all four languages. Whoever requests the whitepaper briefly confirms their email address and is automatically added to the sales team's CRM.
Result
The site is live. New prospects flow into the sales system without any manual work.
Stack
Next.js · next-intl · Docker · Traefik
  • 4 languages
  • 12+ pages per language
  • 0 third-party CDN calls
04Customer portal for a beverage wholesalerPrototypeShow details +
Starting point
A beverage wholesaler took orders by phone, messenger and email — everything was transferred by hand. And every bar or restaurant has its own assortment with its own prices.
Task
A quote for a website plus ordering portal. To make it tangible, the prototype was built as part of the quote itself.
Solution
A working test version: every business logs in and orders from exactly its own assortment. The wholesaler sees all orders in one place, with status and history. Articles are imported straight from the ERP system — nothing is maintained twice.
Result
Shows what two weeks can produce. The quote was not commissioned — the prototype now serves as a demo with sample data, not as a reference.
Stack
React · TypeScript · PostgreSQL

Prototype from a quote that was not commissioned.

  • 193 articles
  • 150 assortments
  • 175 businesses
05How I prove qualityOwn developmentShow details +
Starting point
An own development as a stress test: a simulation core in which saving, replay and multiplayer only work if every machine computes exactly the same result. The smallest deviation is a bug.
Task
Prove that the software stays exactly reproducible while it keeps growing — with tests, not promises.
Solution
Every run is recorded and can be replayed step by step; checksums compare every intermediate state automatically. On top, dedicated tests watch the source code itself — they trip as soon as anyone (including an AI) breaks the rules.
Result
Over 1,300 automated tests green; a complete run is repeated bit for bit. It answers the question everyone has about AI-generated code: how do I know it's right?
Stack
C# · .NET · Godot
  • 1,300+ tests
  • 8,859 steps repeated bit-perfect
  • 4 source-code guards

Services

No price list: after the free initial assessment, every project receives an individual fixed-price quote. You pay for a result, not for hours.

  • PROZESS-AUTOMATISIERUNG▶ Entry point

    Process automation

    The weekly manual chore runs on its own — as a maintained system on your server, not a hobbyist workflow.

    Price
    Individual fixed-price quote after the initial assessment
    Duration
    2–3 weeks

    Code and documentation belong to you. Everything runs on a server in your name — you can take it with you at any time.

  • KUNDENPORTAL

    Customer portal

    Your customers order, book and check their status themselves. Admin area for your team.

    Price
    Individual fixed-price quote after the initial assessment
    Duration
    4–6 weeks

    Code and documentation belong to you. Everything runs on a server in your name — you can take it with you at any time.

  • KI-ASSISTENT▶ Entry point

    AI assistant on your data

    Answers from your own documents (RAG) — as a ready-made solution: hosted as a subscription, or installed encrypted on your server so no document ever leaves your company.

    Price
    Hosted subscription (cancellable monthly) or on-premises installation at a fixed price
    Duration
    4–8 weeks

    Your documents and data always remain yours. The assistant software is licensed — hosted or installed on your server.

  • WEBSITE

    Website with its own backend

    Multilingual, fast, with content, orders and a customer area — no site-builder subscription. Legal notice and privacy policy prepared to current standards — final review by your lawyer or data protection officer.

    Price
    Individual fixed-price quote after the initial assessment
    Duration
    3–4 weeks

    Code and documentation belong to you. Everything runs on a server in your name — you can take it with you at any time.

  • BEGLEITUNG

    Technical guidance

    Securing legacy systems, architecture advice, code review, second opinion.

    Price
    Individual fixed-price quote after the initial assessment
    Duration
    as needed

    Code and documentation belong to you. Everything runs on a server in your name — you can take it with you at any time.

  • BETREUUNG

    Operations & support

    Server, updates, backups, monitoring, business-day response times, named substitute. Available with every package, cancellable monthly.

    Price
    Individual fixed-price quote after the initial assessment
    Duration
    ongoing

    Code and documentation belong to you. Everything runs on a server in your name — you can take it with you at any time.

The four questions everyone asks

„One person — what if you're unavailable?“
In most cases everything runs on a server in your name, and code and documentation are yours from day one — hand-over readiness is part of the definition of done. For operations there is a support agreement with response times and a documented, named substitute.
„AI code is throwaway code.“
That's exactly what the twenty years before are for. The agents speed up the typing, not the judgment.
„We're too small for AI.“
The initial assessment gives you an honest answer on whether it's worth it. Sometimes the answer is no.
„What does it cost?“
A fixed price you know before the project starts — after the free initial assessment. In return you get a system that belongs to you, runs on your server and keeps running without me — no subscription, no lock-in, no rebuild in three years. The one exception: the AI assistant is a ready-made solution — hosted as a subscription or installed encrypted on your server.

How I work

I build software for a business in four steps. Each step has a defined result that you can see and check before the next one begins.

  1. 01

    Understand

    We talk about the process, not about software: who does what today, with which data, where it gets stuck, what should measurably improve. I keep asking until I could explain the workflow without your help — and we agree on what should not be built.

    What you get

    A written problem statement of one to two pages: starting point, goal, users, success criterion, scope boundaries. You confirm or correct it.

  2. 02

    Specify

    The problem statement becomes a specification package: user roles, testable acceptance criteria per feature, edge cases, data model, interfaces, operating environment. I make the technical decisions here and justify them.

    What you get

    The specification package as readable documents, a fixed-price quote, and a project skeleton with version control and automated checks.

  3. 03

    Build — agentic, test-secured

    Implementation feature by feature with AI coding agents, each in three phases: plan, implement, verify (automated tests, type checking, browser testing). Only when all checks are green is the state versioned. Critical parts are cross-read by a second, independent model. The AI never works without a specification, never without tests, never on your production systems.

    What you get

    After every feature, a running version on a test environment you can try yourself, plus a change log. If anything deviates, you get a question — not a silent decision.

  4. 04

    Hand over and operate

    Delivery on a server in your name (containers, reverse proxy, TLS, backups). Credentials stay with you, never in the code. I hand over source code, specification, operations manual and acceptance protocol. Afterwards, optional support with response times and a named substitute.

    What you get

    A system you own and that any other provider could take over. No dependency on me or on someone else's platform.

Portrait of Stefan Diener

About me

Stefan Diener, Dipl.-Ing. (FH)

Precision mechanic, engineer in optical technologies and image processing, twenty years of real-time and AI systems in employment, independent since April 2026.

  • Co-inventor of 2 patents (video matching in camera networks, measuring audience attention)
  • Talks: AWS re:Invent 2017, WKF 2022 (Korea)
  • Based in Rhein-Main / Südhessen, Germany — on-site meetings within the region
My last name, Diener, is German for servant. In Esperanto it becomes servilo — the word for server. I didn't plan that, but it fits: I build systems that serve others, and I make sure they keep running.

Career

  1. 1990s

    Precision mechanic

    Precision as a craft.

  2. 2000s

    Dipl.-Ing. (FH) in optical technologies and image processing

  3. 2002–2011

    Industrial image processing

    For automotive and medical-device manufacturers.

  4. 2012–2026

    Senior engineer at an international AI company

    Including 2015–2019 event and sports tracking for international martial-arts, basketball and fashion events; Coach AI SDK, 3D pose.

  5. 2026

    Independent, ENGILO

    Engineering firm for software & AI. Agentic Coding Master Class.

Contact

Tell me which process costs you time. Within 2 business days you'll receive a written assessment: what's worth doing, what isn't, and roughly what it costs.

I use your details solely to answer your inquiry (Art. 6(1)(b) GDPR) and delete them no later than 6 months after our last contact if no engagement results. Details in the privacy policy.