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 & QAWhat It Costs to Make a Vibe-Coded App Production-Ready
Wavect planning ranges by product shape, the factors that change scope, what a bounded audit can establish, and how to compare hardening with replacement without pretending certainty.
Leadership & TeamsFractional CPO vs Senior PM: Define the Mandate
Compare decision rights, outcomes, availability, management duties, internal context and handover instead of choosing from a universal stage rule.
Leadership & TeamsWhen to Hire a Fractional CPO
Define the product-leadership gap, decision rights, cadence, internal owner, evidence and handover before choosing a fractional model.
Business & RegulationThe One-Page AI Policy for a DACH Company
A practical one-page AI policy baseline for a 5 to 50 person DACH company: approved tools, data rules, literacy, human review, disclosure, escalation, and one owner.
AI & AgentsHow to Cut LLM Token Costs in 2026
Per-token prices are only one part of an AI product's cost. A measured playbook for caching, batching, routing, model selection, context reduction, and self-hosting decisions.
AI & AgentsAI Agent Pilot in 30/60/90 Days
A serious production rollout plan for Austrian SMEs: scope and de-risk, build and shadow, then limited production and handover. The hard parts are permissions, approvals, evals, and a clean handover, not the model.
Leadership & TeamsFractional CTO 30/60/90-Day Plan
You hired a fractional CTO. What should the first 90 days produce? Assess, plan, execute, and the artifacts and running system that survive their departure. Plus when to replace them full-time.
Product & MVPAI MVP Scope Template
Scoping an AI MVP differs from normal software: you replace it works with an eval set, a metric and threshold, a launch gate, and failure handling. A copy-ready SoW template included.
AI & AgentsPermissions-First RAG over SharePoint, Confluence, Drive
The hard problem in enterprise RAG is permissions: never surface a document to a user who cannot see it. Enforce at the retrieval layer, not the prompt, with per-chunk ACLs and identity-aware retrieval.
Get the next field note
One concise email when we publish. No tracking pixels, and no inbox filler.