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.
AI & AgentsCLM-8B Self-Hosting: vLLM, Action Cache and Verifiers
A source-checked deployment guide to CLM-8B: the full encoder behind the small heads, reusable candidates, private APIs and verifier evaluation limits.
AI & AgentsAnyJev: LLM Calibration and Option-Order Bias
A deeper look at Nokia’s AnyJev: why stable answers are not calibrated probabilities, what version 0.2.0 changes and how to evaluate a real router.
Business & RegulationSoftware Agencies in Austria & Vienna for Existing Products
Already have users? Compare Wavect, 9Y, bitsfabrik, craftworks and sclable for the next releases of an existing product, with sourced facts and an explicit publisher disclosure.
AI & AgentsLiteAgents SDK: Per-Turn Routing, Setup and Migration
One agent, different models: a source-checked guide to LiteAgents setup, custom routing, Jev fallbacks and migration without assuming identical tools or permissions.
AI & Agentsmcp-memory-service: Shared Memory for Claude Code and Cursor
Stop reconstructing project decisions when you switch coding tools. A practical shared-memory setup with client configs, debugging checks and clear privacy boundaries.
AI & AgentsClaude Opus 5.5: Best Uses, Prompts and Effort Settings
Where Opus 5.5 is worth trying, what to ask it to deliver and how to verify the result. Five practical workflows, copy-ready prompts and a cost-per-accepted-task pilot.
AI & AgentsLaya and Jev for Business: 6 Practical Workflows
Six practical ways to reduce manual handoffs with Laya and Jev. Includes n8n integration, review-first code and an honest support-routing business case.
Delivery & QAPake: Turn Websites into Desktop Apps Without Electron
One command, a lightweight desktop shell. What Pake really saves, why a Linux AppImage can be 76 MB, and which login and deployment checks matter.
AI & AgentsLaya vs Jev: What the Benchmarks Mean for AI Startups
Can an open specialist undermine a two-year head start? What Laya actually shows, what the Jev comparison misses, and where a defensible AI business can create value.
Get the next field note
One concise email when we publish. No tracking pixels, and no inbox filler.