Opinions, Not Press Releases
Browse a curated front page, then move through focused topic and cluster hubs without losing older work to chronology.
Search every article
Use site search to search the full archive, not only this page.
No posts match your search. Try another term or pick a topic.
Explore by topic
Six durable entry points keep every article close to the main blog hub.
AI and agents
Engineering, operating and evaluating AI systems, coding agents and model infrastructure.
Product and MVP
Validate demand, shape scope and turn uncertain product bets into testable releases.
Delivery and QA
Architecture, production readiness and quality practices for software that must keep working.
Leadership and teams
Fractional leadership, AI-enabled teams and the operating decisions behind delivery.
Business and regulation
Buying software, funding delivery and navigating governance, contracts and regulation.
Web3 and privacy
Blockchain infrastructure, cryptography and privacy technologies evaluated for production use.
Evergreen field notes
- LLM Pseudonymization Gateways: Does the Prompt Leave GDPR Scope?Platforms in this category promise that pseudonymizing a prompt makes a hosted model safe to use. The 2025 CJEU ruling and the EDPB guidance say something narrower. Here is the evidence a buyer actually has to collect.
- Micro Agency vs Mid-Size Agency: How Big Should Your Software Partner Be in 2026?The one-person agency versus micro agency argument is a debate between sellers. Here is the buyer's version, with the team-size research, the 2026 agency margin data, and the four clauses that make a small partner safe to hire.
- Qwen3.8-27B: Self-Hosted Computer-Use Agents Without Exporting ScreenshotsAn open-weight model now leads desktop-operation benchmarks. What that changes for back-office automation you cannot send to a hosted API.
- Transformers.js Browser AI: When Local Inference Belongs in Your ProductA production guide to private in-browser AI: verified adoption, WebGPU and WASM, real cost, privacy boundaries, use cases, fallbacks and a 30-day pilot.
- Stateful LLM Platform Production ArchitectureAn anonymized field guide to persistence, tenant access, long-running jobs, external interfaces, deployment controls and continuous QA without a full rewrite.
- AI 3D Model Generators for Game Development: 2026 GuideWhich AI 3D tools can help a game team, and which outputs still need an artist? Compare hosted and self-hosted options, quality gates, licensing and engine handoff.
- AI-Ready Company Wiki: Architecture and Build GuideA buyer-focused blueprint for company knowledge that humans can edit and AI agents can retrieve with the same permissions, sources and review loop.
- AI Agent Contract Signing: eIDAS QES Integration GuideA developer and buyer guide to binding AI-generated contracts to human approval, remote QES, ID Austria or EUDI Wallet flows, validation and audit evidence.
- How to Self-Host LiteLLM in Production: 2026 GuideA security-first LiteLLM deployment guide for teams choosing their own AI gateway: architecture, Postgres, Redis, keys, upgrades, cost and go-live checks.
- Internal AI Agent Marketplace: A 2026 Enterprise Build GuideBuild a governed internal agent catalog employees will use. Architecture, listing contract, identity, context, evaluations, approvals, metrics and a 90-day rollout.
- Is Linux the Best OS for AI Agents? A 2026 Infrastructure GuideLinux gives AI agents a mature shell, open interfaces and several isolation layers. This guide shows where it wins, where it does not, and how to deploy agents without handing them the host.
- How to Make AI Writing Sound Human with Agent SkillsNo AI Slop, i-have-adhd and book-to-skill solve different writing problems. Here is how to combine, test and govern them without erasing your voice.
- PII Redaction Before LLM Prompts: A Practical PipelineCompare Presidio, OpenAI Privacy Filter and managed DLP services. Then build a reversible prompt gateway that protects personal data without destroying task context.
- Why 40% of AI Agent Projects DieEight patterns we keep seeing across AI agent engagements. What they look like, how they kill the project, and the cheap fix when caught early.
- The MVP Is Dead. Build a Minimum Credible Product.AI made prototypes cheap, not product judgment. The traditional MVP's roughness now damages the signal it was meant to collect. A practical case for building less, finishing one trustworthy path, and measuring evidence that deserves the next investment.
- Why Test-Driven-Development pays offTesting has created the illusion that it is costly, slows down your development speed and blocks your engineering department. When in reality, it saves you BIG money.
- Fractional CTPO vs CTO and CPOWhen one combined head owning product and engineering beats hiring a fractional CTO and CPO separately, the eight-engineer split point, and the single-point-of-failure trade-off.
- Pricing Software Projects the Right WayEveryone hates hourly pricing, so they ask for fixed prices instead. Here's the problem, fixed pricing on software projects is just as broken.
- Smart Contract Security Checklist (30 Items)The 30-item internal checklist we run on Solidity code before sending it to an external auditor. Compiler, access control, reentrancy, gas surfaces.
Latest articles
Nine articles per page, ordered by publication date.
Delivery & QACursor Origin vs GitHub: Should Your Team Switch?
Cursor now hosts code, but Origin is still an early beta. Compare sync behavior, CI, governance, price and a low-risk pilot before moving your source of truth.
AI & AgentsPika Audio Models API Pricing: Is SFX Really 20x Cheaper?
Pika lists SFX at $0.0002 per second, plus three more audio models. See the real break-even, API limits, quality gates and production fit before you switch.
AI & AgentsThunder Compute's $13M GPU Virtualization Bet: Enterprise Buyer's Guide
Thunder Compute says GPU pooling can recover stranded capacity. Compare network virtualization with MIG, vGPU and passthrough, then scope a measurable enterprise pilot.
AI & AgentsOpenViking Review 2026: Is Filesystem Memory Production-Ready?
Buyer review of OpenViking for agent memory and RAG: architecture, AGPL risk, security controls, operating cost and a measurable two-week pilot.
AI & AgentsLLM-as-a-Verifier Explained: Architecture, Costs, and Production Fit
A technical buyer guide to fine-grained LLM verification: how logprob scoring and pivot tournaments work, what the benchmarks prove, and how to pilot it safely.
Delivery & QAMoneyPrinterTurbo Review 2026: Free AI Video, Real Costs
MoneyPrinterTurbo turns a topic into a narrated short, but free code is only the start. See its setup, hidden costs, licensing, platform risk and production fit.
AI & AgentsAirLLM on 4 GB VRAM: How Layer-Wise Inference Really Works
AirLLM can execute models far larger than GPU memory by streaming weights layer by layer. Separate the measured VRAM claim from disk, latency, quantization and production reality.
AI & AgentsTrueForge Review: Is the Open-Source Agent Harness Production-Ready?
A buyer-focused review of TrueForge, its agent loop, context controls, benchmark economics, deployment modes and enterprise production gaps.
AI & AgentsAgent-Readable Websites: llms.txt, Markdown Mirrors and What Breaks
Four surfaces decide whether an AI answer engine can read you, and every failure mode is invisible in a browser. Here is the list our own build gate has caught.
Follow the work that matters to you
Get a short email when we publish something new. Follow the whole blog or only the problems you care about.