Skip to content
_CORE
AI & Agentic Systems Core Information Systems Cloud & Platform Engineering Data Platform & Integration Security & Compliance QA, Testing & Observability IoT, Automation & Robotics Mobile & Digital Banking & Finance Insurance Public Administration Defense & Security Healthcare Energy & Utilities Telco & Media Manufacturing Logistics & E-commerce Retail & Loyalty
References Technologies Blog Know-how Tools
About Collaboration Careers
CS EN DE
Let's talk
Home / Blog
CORE BLOG

Technology, Architecture, AI, DevOps & Security

Practical articles from real projects. From enterprise architecture to AI agents — we share what works in production.

510
Articles
8
Categories
15
Years of experience
Showing 20 of 510 articles
Edge AI and On-Device ML — Intelligence Without the Cloud
25. 08. 2024ai

Edge AI and On-Device ML — Intelligence Without the Cloud

AI on edge devices: lower latency, better privacy, offline capability.

Synthetic Data for AI Testing — Quality Without Privacy Issues
05. 08. 2024ai

Synthetic Data for AI Testing — Quality Without Privacy Issues

Synthetic data solves GDPR compliance, bias, and lack of training data.

Passkeys and FIDO2 — End of the Password Era in Enterprise
15. 07. 2024development

Passkeys and FIDO2 — End of the Password Era in Enterprise

Apple, Google, and Microsoft have adopted passkeys. Implementation aspects.

Post-Quantum Cryptography — Prepare for the Quantum Threat
28. 06. 2024development

Post-Quantum Cryptography — Prepare for the Quantum Threat

NIST finalized post-quantum standards. The harvest-now-decrypt-later threat.

DORA — EU Digital Operational Resilience for Finance
10. 06. 2024development

DORA — EU Digital Operational Resilience for Finance

The DORA regulation (Digital Operational Resilience Act) is changing the rules of digital resilience for banks,...

AI Observability — Monitoring LLMs in Production
08. 06. 2024ai

AI Observability — Monitoring LLMs in Production

LLMs in production need observability. Latency, cost, quality monitoring.

Passkeys — Passwordless Authentication Finally in Practice
22. 05. 2024ai

Passkeys — Passwordless Authentication Finally in Practice

Passkeys replace passwords with biometrics and cryptography. How they work, why they're more secure, and how to...

WebAssembly on the Server — Not Just for Browsers
20. 05. 2024development

WebAssembly on the Server — Not Just for Browsers

WebAssembly on the server with WASI. Sandboxed execution, edge computing.

Multi-Agent Orchestration — When One AI Agent Isn't Enough
02. 05. 2024ai

Multi-Agent Orchestration — When One AI Agent Isn't Enough

CrewAI, AutoGen, LangGraph — frameworks for multi-agent systems.

Function Calling and Tool Use — LLMs as Real-World Orchestrators
10. 04. 2024ai

Function Calling and Tool Use — LLMs as Real-World Orchestrators

Function calling transforms LLMs from text generators into action agents.

AI Governance in Practice — From Principles to Implementation
25. 03. 2024ai

AI Governance in Practice — From Principles to Implementation

How to build an AI governance framework for responsible AI deployment.

RAG — Retrieval Augmented Generation in Practice
18. 03. 2024ai

RAG — Retrieval Augmented Generation in Practice

How RAG (Retrieval Augmented Generation) works and why it's critical for enterprise AI. Architecture, embeddings,...

Google Gemini — The Third Player in the Enterprise AI Ring
05. 03. 2024ai

Google Gemini — The Third Player in the Enterprise AI Ring

Google Gemini enters the enterprise AI market. Native multimodality, million-token context.

Advanced RAG Patterns — From Naive RAG to Production Quality
18. 02. 2024ai

Advanced RAG Patterns — From Naive RAG to Production Quality

Advanced techniques: hybrid search, reranking, query decomposition, corrective RAG.

Ollama — LLM on Your Laptop in 5 Minutes
30. 01. 2024ai

Ollama — LLM on Your Laptop in 5 Minutes

Local LLM inference has never been easier. Ollama makes models accessible locally.

Mistral — The European LLM That Exceeds Expectations
12. 01. 2024ai

Mistral — The European LLM That Exceeds Expectations

French Mistral AI delivers models competing with GPT-3.5. Mixtral 8x7B MoE is a breakthrough.

AI Coding Assistants — GitHub Copilot, Cursor and the Future
08. 12. 2023ai

AI Coding Assistants — GitHub Copilot, Cursor and the Future

AI coding assistants are transforming how we write code. A comparison and productivity analysis.

Kubernetes Gateway API — The Successor to Ingress Worth Adopting
22. 11. 2023ai

Kubernetes Gateway API — The Successor to Ingress Worth Adopting

Gateway API is the next generation of Kubernetes ingress. More expressive and more secure.

ChatGPT in Enterprise — Secure Deployment Without Compromises
06. 11. 2023ai

ChatGPT in Enterprise — Secure Deployment Without Compromises

How to securely deploy ChatGPT in an enterprise environment. Azure OpenAI, data governance, compliance, and...

LLM Evaluation — How to Measure the Quality of Text-Generating AI
05. 11. 2023ai

LLM Evaluation — How to Measure the Quality of Text-Generating AI

Measuring LLM output quality. A framework for evaluation from automated metrics to human evaluation.