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 & QAQA for AI-Generated Code
A risk-based verification guide for AI-assisted code, covering trust boundaries, failure paths, dependencies, concurrency, operational evidence, and the limits of any review.
Delivery & QAFrom Lovable and Cursor Prototype to Production: The Migration Checklist
Getting to a demo is fast. Getting to production is a separate project. The checklist we run to harden an AI-IDE prototype, auth, data, secrets, hosting, and the keep-vs-rebuild call.
Delivery & QAVibe-Coded Software Audit: What to Check Before Launch
A risk-based review of AI-assisted software, the evidence to examine before launch, and how to prioritize remediation.
AI & AgentsRAG Production-Readiness Checklist for EU Companies
A RAG prototype is only a starting point. A risk-based review of retrieval, grounding, evaluation, cost, privacy, transparency, prompt injection, and permission-aware retrieval.
Business & RegulationMVP Development for Startups in Austria: Agencies, Cost and Selection 2026
A sourced comparison of nine Austrian MVP providers by fit, public pricing, stated timeline, presence and proof, with Wavect's commercial interest disclosed and missing facts left unguessed.
Product & MVPHow Much Does an AI MVP Cost in Austria in 2026?
Wavect's EUR planning bands by tier, the assumptions behind them, build/buy/fine-tune tradeoffs, ongoing costs, and Austrian funding routes that require case-specific eligibility checks.
Business & RegulationWhen Not to Hire Wavect
Six situations where Wavect may be the wrong fit, the alternatives to evaluate, and the current engagement models Wavect actually offers.
Business & RegulationCan a Software Studio Claim Austria's Forschungsprämie?
Austria's Forschungsprämie credits 14% of qualifying R&D expenditure to the tax account. Current eligibility, cost-base, FFG-opinion, contract-research, grant, and German-comparison caveats.
AI & AgentsWhen Is an LLM Eval Worth Building? Cost, ROI, and Trusting the Judge
Scale LLM evaluation to impact, exposure, change frequency, and uncertainty. A practical guide to test design, judge validation, datasets, and total evaluation cost.
Get the next field note
One concise email when we publish. No tracking pixels, and no inbox filler.