FROM THE TRENCHES Issue №354

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.

SuperPenguin editorial illustration about AI cost attribution per pull request, customer and feature AI & Agents

SuperPenguin: AI Cost per PR, Customer and Feature

What did a merged PR cost, and what does each customer cost to serve? A practical SuperPenguin guide with billing reconciliation, worked examples and an optimization prompt.

Editorial illustration of product dashboard findings becoming an animated update AI & Agents

Claude Dashboards + Motion: From KPIs to Video

Turn a reviewed product metric into a short animated update. A practical Claude Dashboards and Motion workflow with a cohort example, two prompts and sharing rules.

Two turquoise interface panels representing interactive answers and application components AI & Agents

OpenAI Intelligent UI vs OpenUI: Generative UI for Business Apps

ChatGPT’s new interface raises a practical question: how do generated views become reliable business workflows? Compare APIs, actions, persistence and evaluation.

Three separate branch lanes feeding one shared application preview Delivery & QA

GitButler for Parallel AI Agents: Multiple Branches, One Build

Let agents work on separate branches in one running application. Learn the CLI workflow, hidden dependencies, branch checks and what multiplayer still needs.

Greptile Base vs Plus vs Apex: A PR Review Budget Delivery & QA

Greptile Base vs Plus vs Apex: A PR Review Budget

Choose Greptile review depth by change risk. Compare credits, monorepo rules and a pilot that measures verified findings and human triage time.

Wally by RunAnywhere: Cost per Accepted Coding Task AI & Agents

Wally by RunAnywhere: Cost per Accepted Coding Task

Evaluate Wally by completed coding tasks, retries and full cost. Separate hosted inference from local execution and test provider changes fairly.

Vendo for SaaS: Tenant Isolation and Approval Boundaries Delivery & QA

Vendo for SaaS: Tenant Isolation and Approval Boundaries

Plan a Vendo SaaS integration with two tenants, role changes, approvals and restart tests. Learn which production responsibilities remain yours.

Arga Labs vs Archal: Stateful Agent Integration Tests Delivery & QA

Arga Labs vs Archal: Stateful Agent Integration Tests

Compare Arga and Archal for repeatable integration tests. Use a GitHub-to-Slack protocol covering duplicate events, interrupted runs and forbidden writes.

Canary AI QA: Test Defect Detection, Not Benchmark Scores Delivery & QA

Canary AI QA: Test Defect Detection, Not Benchmark Scores

Evaluate Canary alongside Claude Code or Codex with known defects, clean controls and independent checks. Understand what QA-Bench v0 actually measures.

Inbox, without the noise

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 →