Practical decisions for AI and software
Technical guides to choose models, verify software and plan delivery.
Search every article
Search the full article text.
No posts match your search. Try another term or pick a topic.
Latest articles
New comparisons, practical guides and engineering lessons.
Open-Weight LLMs 2026: DeepSeek, Qwen, Kimi, GLM, Llama and Muse
Compare open-weight LLMs in November 2026 by checkpoint license, context and deployment hardware, from Qwen3.8-27B and Muse Glimmer to cluster models.
AI Consulting in Austria 2026: An Honest Guide for SMEs
AI consulting in Austria: realistic scoping costs, SME use cases, AI Act duties and November 2026 funding status, including the end of KMU.DIGITAL.
The Bottleneck Was Never Intelligence. It Was Context.
Rakuten reported a seven-hour Claude Code session on vLLM with 99.9% numerical accuracy for one method. What the vendor case study shows, what it does not, and how to build a reviewable agent workflow.
ChatGPT Enterprise vs Copilot vs Custom RAG
Which should a DACH company shortlist? A neutral procurement guide to workflow fit, product terms, location controls, permissions, compliance roles, and total operating cost.
EU Data Residency for AI APIs in 2026: Provider Guide
Compare EU storage and inference guarantees across OpenAI, Azure, Mistral, AWS and self-hosting. Current endpoints, transfer caveats and a procurement checklist.
Lovable, Bolt, and Replit App Due Diligence
Before you raise or sell on a vibe-coded app, three questions decide whether it survives diligence: is it safe, do you own it, can anyone maintain it? The security, IP, and investor checklist.
AI funding in Austria and the EU: 2026–2027 grants
Which AI grants are open in Austria and the EU? Check regional funding, FFG and 2027 deadlines, then calculate your own contribution before signing a quote.
How to Roll Out AI Internally in 2026
A staged internal AI rollout: align the team, map the process and alternatives, define a baseline, settle data and risk questions, pilot one bounded workflow, then expand or stop on evidence.
MCP vs RAG vs Agent Skills vs Custom GPTs
Not four answers to one question, but four layers: RAG for knowledge, MCP for connectivity, Skills for procedure, Custom GPTs as a packaged surface. A decision tree, and why you usually compose them.
Get the next field note
One concise email when we publish. No tracking pixels, and no inbox filler.
Facing one of these decisions right now? Talk it through with us →