Popular searches
Hamburger Menu
Logo der codecentric AG, einem in Deutschland führenden IT-Consulting Unternehmen
    //

    The Gap Inverted

    8.9.2026 | 1 minutes reading time

    Delphi - Temple of Apollo
    //

    Learn more about software modernization at codecentric

    From retro computer, a green-glowing data stream goes to modern laptop as a visualization of the software modernization
    Software modernization: Holistic. Transparent. Forward-looking.

    Are your existing systems slowing you down?
    We can help you modernize them – whether it's optimization, transformation or rebuild. Together, we'll make your software fit for the future – with modern technology, a clear strategy and a strong team at your side.

      Platform Engineering mit codecentric
      Platform engineering for greater efficiency and innovative power

      Use platform engineering to achieve a scalable and efficient development process. We will advise you on the potential for optimization in your specific situation.

      • Platform engineering
      • DevOps
      • Accelerate
      Illustration: Person mit Notebook in Wolke. Charts, Puzzleteile und Zahnräder stellen verschiedene IT-Anforderungen dar.
      Cloud native: Consulting and software development

      From strategy to implementation: our certified experts (Azure, AWS, Google) develop bespoke solutions for your optimal cloud solution.

      • Cloud native
      • DevOps
      • Accelerate
      //

      More articles in this subject area

      Discover exciting further topics and let the codecentric world inspire you.

      Retrieval Augmented Generation: Architecture und Design-Decisions

      LLMs are incredibly useful tools that bring a lot of world knowledge with them. Knowledge that was learned during the training of the LLM. As a result, they not only master programming languages, but also bring along a lot of knowledge about frameworks...

      • Generative AI
      • LLM

      7.9.2026 | 1 minutes reading time

      Hendrik Schawe

      The Bottleneck in the AI Coding Loop

      Benjamin Font Pera described the coding loop as the innermost circle in Loop Engineering, Harness Engineering, Context Engineering: what's the difference?. The agent generates code, verifies it and adjusts it. This round repeats until it considers its...

      • LLM
      • Generative AI
      • Software development

      3.9.2026 | 1 minutes reading time

      Johannes Barop

      Local LLMs in a software developer's day-to-day work

      Today, developers who want to be productive increasingly rely on AI-powered coding agent harnesses like Claude Code as sparring partners. But which models actually deliver the best results in daily code usage? Can this compute-intensive work be offloaded...

      • Generative AI
      • Software development
      • LLM
      • AI

      13.8.2026 | 1 minutes reading time

      Closing the Loop: A Prompt Iteration Workflow for Databricks Genie

      Part 03 covered the improvement loop in a single sentence: identify weak categories, examine the failures, apply the fix, re-run, compare. That was accurate as far as it went, but "apply the fix" is doing a lot of hidden work. In practice, it means choosing...

      • AI
      • LLM
      • Generative AI

      10.8.2026 | 1 minutes reading time

      Niklas Niggemann

      Reliable by Design: Building an Evaluation Harness for Databricks Genie

      The first two parts of this series established the principles. A semantic layer gives your organization a governed vocabulary that both humans and AI can trust. A Data Flywheel gives your team the operational discipline to keep GenAI systems improving...

      • Generative AI
      • LLM
      • Platform engineering

      4.8.2026 | 1 minutes reading time

      Niklas Niggemann

      Integrating LLMs with Ollama and Spring AI

      Introduction Not every AI use case has to talk to a cloud API. For prototyping, offline development, or handling sensitive data, running a Large Language Model (LLM) locally is often the better choice. Ollama makes this straightforward: it downloads,...

      • AI
      • LLM
      • Software development

      3.8.2026 | 1 minutes reading time

      Tobias Trelle

      Managing the Hidden Technical Debt of Generative AI

      A well-governed semantic layer gives your organization a foundation it can trust. But the moment you start building GenAI applications on top of that foundation, conversational interfaces, AI-powered data assistants, autonomous agents, a new category...

      • LLM
      • AI
      • Platform engineering
      • Data

      28.7.2026 | 1 minutes reading time

      Niklas Niggemann

      The Semantic Layer: Shared Business Meaning as Infrastructure

      The right starting question for any data initiative is not what could we do with our data? but which business decision should get better, and how would we know if it did? A semantic layer is the infrastructure that makes that question answerable with...

      • Infrastructure
      • Platform engineering
      • LLM
      • Data

      22.7.2026 | 1 minutes reading time

      Niklas Niggemann

      Genie One: How Databricks Is Reshaping Its Data Assistant

      Databricks has reworked Genie, moving it from a tool focused on answering questions about data toward one intended to help users act on it. This shift is packaged under Genie One, alongside two related developments, Genie Agents and Genie Ontology, that...

      • LLM
      • Generative AI
      • Big Data
      • Data
      • Compliance

      14.7.2026 | 1 minutes reading time

      Niklas Niggemann

      Selfhosting AI models in your kuberenetes clusters

      AI is on everybody's mind nowadays. While some organizations have the possibility to use externally hosted models from e.g. Anthropic, Google, ..., others might not have those options. There are multiple options to host AI models on your own hardware...

      • LLM
      • AI
      • Compliance
      • regulatory

      3.7.2026 | 1 minutes reading time

      Brainstorming With AI – When to Play Devil's Advocate

      Brainstorming With AI — When to Play Devil’s Advocate Part of the series Domain-Driven Design Meets AI. Every project starts with a blank canvas, and the blank canvas is where good ideas go to die. You put 8–12 people in a room, point at an empty whiteboard...

      • DDD
      • Generative AI
      • LLM

      15.6.2026 | 1 minutes reading time

      From Inference to Governance: Why Agent Metadata Matters When LLMs Already...

      Modern LLMs demonstrate strong capability in inferring meaning from column names. A tool such as Genie can typically resolve pct_cust_attrit_q to "churn" or map rev_mrr_usd to a"MRR" through pattern recognition alone. On a small, well-structured table...

      • AI
      • LLM
      • Big Data
      • Database

      15.5.2026 | 1 minutes reading time

      Niklas Niggemann

      AI as a Design Partner — Drafter, Validator, Provocateur

      Part of the series Domain-Driven Design Meets AI. The previous post introduced the Synergetic Blueprint as the structured process that turns DDD methods into a coherent end-to-end design flow, and made the case that AI augments every step of it. This...

      • DDD
      • LLM

      14.5.2026 | 1 minutes reading time

      The Accessible Domain: Knowledge Engineering for AI-Assisted Development

      The Old Promise In the late 1970s, Stanford computer scientist Edward Feigenbaum coined the term "Knowledge Engineering". He described it as the process of extracting expert knowledge, structuring it, and making it usable within a software system. Central...

      • Generative AI
      • AI
      • LLM
      • Software Modernization
      • Software development

      11.5.2026 | 1 minutes reading time

      Johannes Barop

      Benjamin Font Pera

      Data Quality Powers AI Analytics: Building Trustworthy Genie Spaces in...

      Garbage In, Garbage Out. This computing truism has never been more critical than in the age of AI. Large Language Models don't amplify poor data quality, they wrap it in confident-sounding prose that can mislead even experienced users. As organizations...

      • Generative AI
      • LLM
      • AI
      • Data

      7.5.2026 | 1 minutes reading time

      Niklas Niggemann

      The Synergetic Blueprint Revisited — and Why AI Changes Everything

      From Workshop to Working Software — the Gap Nobody Talks About Most teams that adopt Domain-Driven Design invest heavily in workshops. Domain Storytelling sessions, EventStorming boards, context mapping exercises — the collaboration is real, and the ...

      • DDD
      • LLM

      28.4.2026 | 1 minutes reading time

      Is Spring Boot Becoming Obsolete?

      In March 2026, we kicked off a modernization project for a client. Spring Boot was an obvious choice. There was a strategic decision behind it. There was existing know-how. There was existing infrastructure. The team was set. The work began. One of the...

      • Generative AI
      • LLM
      • AI
      • Software development
      • Software architecture

      27.4.2026 | 1 minutes reading time

      Johannes Barop

      The Ralph Wiggum Loop: Autonomous Code Generation with a Fresh Context

      Ralph Wiggum is the simple-minded boy from The Simpsons who says things like "I'm learnding!" and eats glue. Of all people, he is now the namesake for a technique for autonomous code generation. The idea behind: If the thought of letting code be generated...

      • Generative AI
      • LLM
      • AI
      • Software development

      6.4.2026 | 1 minutes reading time

      Johannes Barop

      From Domain Story to Prototype - Specification-driven Prototyping in DDD...

      You've just run a great Domain Storytelling workshop. The Miro board is covered in pictograms, numbered arrows, and work objects — stickies everywhere, connections between everything, the whole board alive with the domain's logic. Frames hold the Domain...

      • DDD

      2.4.2026 | 1 minutes reading time

      From Stories to Code: How Domain Storytelling and EventStorming Give LLMs...

      The Broken Promise of AI-Assisted Development By now, most development teams have tried using an LLM to generate code. The results are familiar: syntactically correct, superficially plausible, and frequently wrong in ways that take hours to diagnose....

      • DDD
      • AI

      4.3.2026 | 1 minutes reading time