From our SaaS audits
What we find inside SaaS companies
Patterns from the technical due diligences we run for investors and boards.
AI
Your limit will reset at 12pm
Half of today's AI best practices are coping mechanisms for temporary scarcity, not timeless engineering insights. Geoffrey Dhuyvetters traces the arc from SMS bundles to token limits, and argues the price curve only goes one direction.
The SaaS audit bingo card: insights after auditing 190+ SaaS companies
After auditing 190+ SaaS companies, the same patterns keep showing up: a CTO who does everything, documentation nobody updates, a backlog from 2019. Here's what the bingo card looks like, and what AI is changing about it.
Your Claude Code is burning through tokens: here's how to fix it
Five idle plugins can burn 55,000 tokens before you type a word. Here's how to diagnose token consumption in Claude Code and cut overhead through plugin management, profiles, and context hygiene.
Agentic engineering is a bottleneck
The standard AI-assisted dev loop has created a new bottleneck: us. Peter Eysermans describes how deterministic orchestration via n8n, with GitHub as shared memory, gets the human off the loop without sacrificing quality.
You're reviewing the wrong file
When an AI agent gets a requirement wrong, the mistake lives in the test assertions, not the implementation. Domain knowledge catches it, not coding skill.
Who teaches the next generation?
AI has removed the junior work that used to build software engineers. Seven other industries faced the same disruption and didn't agree on an answer.
Stop calling it vibe coding
"Vibe coding" has become shorthand for bad engineering to some people, but does the label hold up? This post unpacks how a playful term coined by Andrej Karpathy became a verdict, and why that's costing teams more than they realise.
Beyond prompting: read, verify, implement, learn
LLMs generate code fast, but knowledge debt accumulates quickly. The fix is living documentation, and this post shows how to turn your LLM into the partner that maintains it automatically.
Nobody learned a city from a map
The fastest way to learn agentic development is to stop studying it: move in, extract repeatable patterns into skills, and reflect to compound.
Bots and Boundaries: Two problems, one policy (Part 3)
In part three, we look at both sides of the AI contribution debate. A working patch, real demand, never submitted, rejected because AI was involved. But maintainers are unpaid volunteers, and AI halved the cost of contributing without touching the cost of review. Both sides have a point.
The artificial Turk and our role as software experts
We smile at the 18th-century crowd for being swept up by a box with a man inside, yet today it's easy to hand ChatGPT a vague idea and treat the PRD it returns as gospel. Generative AI is genuinely powerful. We get the best from it when we bring both enthusiasm and a critical eye.
From opt in to default
Developers don't skip standards because they're careless, they skip them because there are fifteen things to remember and the code was the hard part. The real question isn't which tasks your LLM handles well. It's what's still slipping through ungated.
Hire for divers
The AI wave is here, and the industry is already splitting into two: those adapting fast and those falling behind. The gap is widening quickly.
Three Claudes walk into a codebase
The machines aren't replacing developers, they're promoting them. You're no longer just writing code; you're managing agents, reviewing output, and setting standards. Three Claudes walk into a codebase, and suddenly you're a manager.
Running multiple Claude accounts without logging out
Managing multiple Claude Code accounts across machines gets messy fast. Jean-Claude keeps the useful parts in sync, separates account-specific config, and makes switching between personal, team, and client setups far less painful.