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.
Delivery & QA4 Software Agencies in Austria for Development and QA (2026)
Wavect leads this focused shortlist with Cloudflight, Qualysoft and TechTalk. Compare development and testing scope, dated rankings and release evidence.
Delivery & QAEnterprise Software: Adding a Specialist Alongside Your System Integrator
Bring a specialist into an existing enterprise programme. A worked brief clarifies the contribution, interfaces, decisions, acceptance and handover.
Business & RegulationGoogle Harness²: Setup, Benchmarks and the Real Cost
Better agent results without retraining the model? Read what Google Harness² changes, what its benchmarks prove, and why a safe pilot needs a cost and acceptance boundary.
Delivery & QANVIDIA Run:ai Open Source: GPU Fleet vs Software Factory
GPU orchestration just became easier to inspect and adopt. Compare Run:ai modules, Community Product terms and the missing task-to-patch acceptance layer.
Delivery & QAUltramarine 1 Flash for document agents: pricing, API limits and a migration test
The 60x claim gets attention. Document fidelity, API compatibility and human review decide whether switching actually pays.
Business & RegulationAI Agent Hours + Human Hours: Why Clients Should Push Back
AI makes delivery faster. Should it also create a second clock on your invoice? The client case for accepted results, clear budgets and accountable software delivery.
AI & AgentsCue Turn Detection: Phone Numbers, Benchmarks and Limits
A pause is not a finished phone number. What Pype’s Cue v1 improves, what the benchmarks measure, and how to test correct, confirmed capture.
AI & AgentsRTK AI 1.0: Real Token Savings, Setup and Licensing
RTK 1.0 goes beyond shell-output filtering. Understand the 1.0.1 release, license split, proxy limits and the difference between a smaller transcript and a lower bill.
Business & RegulationAnthropic’s self-replicating AI warning: the local AI takeaway
A security warning with an unexpected local-AI lesson. Separate the three experiments, check the speed arithmetic and make ownership testable.
Get the next field note
One concise email when we publish. No tracking pixels, and no inbox filler.