FROM THE TRENCHES Issue №310

Practical decisions for AI and software

Technical guides to choose models, verify software and plan delivery.

Latest articles

New comparisons, practical guides and engineering lessons.

Local multimodal AI coding assistant with voice, OCR, reasoning and privacy controls AI & Agents

Local Multimodal AI Coding Assistant: Voice, OCR and Privacy

A reference architecture for private voice, screen and code workflows, with verified data boundaries, security controls and a 30-day buying plan.

Kevin Riedl
Read
Stripe invoice PDF next to a structured EN 16931 dataset, with the validation, archive and correction systems a billing stack still needs Business & Regulation

Stripe Billing and E-Invoicing 2027

Stripe produces PDFs, not structured e-invoices. What a B2B SaaS has to build before Germany’s 2027 mandate, and what it can safely buy.

Kevin Riedl
Read
A browser window connected to semantic detection, guarded actions and persistent workflow state Delivery & QA

Tampermonkey Workflow Automation

When a userscript is a sound automation layer, how to keep it resilient, and when the workflow belongs in a backend integration instead.

Kevin Riedl
Read
One shared cross-platform codebase branching into AI-maintained native applications Delivery & QA

Will AI Kill Cross-Platform Frameworks?

If AI makes native code cheap, does one shared Electron, Flutter or React Native codebase still win? A cautious look at the economics.

Kevin Riedl
Read
DeepSeek V4 Flash 0731 model weights fitted into GB10, Strix Halo and Gorgon Halo unified memory AI & Agents

DeepSeek V4 Flash 0731 on One AI PC: What Actually Works?

Can one GB10, Strix Halo or Gorgon Halo run DeepSeek V4 Flash 0731? A buyer-focused reality check on memory, quantization, privacy, observability and production readiness.

Kevin Riedl
Read
QM gives employees and shared Slack rooms isolated AI agent workspaces connected to one policy-controlled core AI & Agents

YC QM Agent Review: Is Quartermaster Ready for Work?

Quartermaster gives employees and shared rooms isolated AI agent workspaces. Review QM’s GitHub architecture, security postures, deployment ownership and pilot fit.

Kevin Riedl
Read
jcode and Claude Code agent harnesses compared across memory, startup, context and team adoption AI & Agents

jcode vs Claude Code: Is the Rust Harness Worth Switching To?

The viral RAM numbers are real but easy to misread. A fact-checked buyer review of jcode’s Rust architecture, passive memory, agent-grep, self-dev mode and team adoption risks.

Kevin Riedl
Read
Lightpanda headless browser production evaluation for AI agents AI & Agents

Lightpanda Browser for AI Agents: Production Guide

Lightpanda reports 9x faster execution and 16x lower memory than Chrome. See what the benchmark proves, where compatibility ends, and how to run a safe production pilot.

Kevin Riedl
Read
Graph engineering connects AI agent workflows, experiment lineage and shared knowledge AI & Agents

Graph Engineering for AI Agents: When Does a Knowledge Graph Pay Off?

A buyer-focused guide to execution graphs, experiment DAGs and knowledge graphs, including when to skip them, what provenance requires and how to run a measured pilot.

Kevin Riedl
Read
Inbox, without the noise

Get the next field note

One concise email when we publish. No tracking pixels, and no inbox filler.