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.
CLIProxyAPI: Run GPT-5.6 Sol Inside Claude Code
Keep Claude Code’s agent harness and route the model calls to GPT-5.6 Sol. This copy-paste setup fixes the incomplete viral alias, locks down the proxy, and shows how to verify every layer.
Floci vs LocalStack: AWS Emulator Review for CI in 2026
A fact-checked buyer guide to Floci, LocalStack, AWS SAM and real AWS: fidelity, service coverage, licensing, CI fit and a low-risk migration test.
Miso TTS Self-Hosted vs API: Cost, Latency and VRAM Reality
Miso TTS is expressive and open-weight, but the 110 ms claim belongs to its hosted H100 API, not local inference. Compare hardware, pricing, licensing and production risk before choosing.
Enterprise MCP Authorization Architecture
OAuth 2.1, audience-bound tokens and no token passthrough are the spec’s hard rules. The rest, multi-tenant isolation, per-tool scopes, delegated access and audit, is a reference design. Here is the whole trust boundary in two diagrams.
EU AI Act Article 50 Checklist for SaaS and AI Agents
Article 50 has applied since 2 August 2026. Audit chatbot and agent disclosures, machine-readable marking, deepfake labels, public-interest text, logging, and the evidence kept for enforcement.
Compress RAG Vectors to 2 Bits: Is Data-Oblivious Quantization Production-Ready?
Qdrant 1.20 adds TurboQuant storage options, and TurboVec 1.1.2 changes the rollback plan. Compare raw code sizes, recall and real collection costs.
LMCache Reported 13.7x Lower Mean TTFT with a Shared KV Cache
LMCache reported mean time-to-first-token falling from 3.98s to 0.29s in one multi-turn Qwen3-235B benchmark. Here is what the result shows, what it does not prove, and how to test reuse on your own workload.
Lossless LLM Weight Compression vs 8-bit GGUF: What Is Ready for Production?
A fact-checked decision guide to the GLM-5.2 result, exact BF16 decoding, Q8 quantization, prior systems, runtime evidence, fleet economics and a 14-day pilot.
Paid Pilot vs PoC vs Design Partner: Which One Proves Demand?
Decision guide for choosing the right evidence test: technical feasibility, customer learning or willingness to pay, with a seven-condition paid-pilot scorecard and contract brief.
Get the next field note
One concise email when we publish. No tracking pixels, and no inbox filler.
Facing one of these decisions right now? Talk it through with us →