This is the first edition of my rebranded newsletter, straight from my desk. Every other week, I'll write something about what we're seeing across the software companies we work with at madewithlove. Think audit insights, AI in real codebases, technical due diligence, CTO struggles, the patterns we keep running into, ...

Hope you enjoy!

If you want to stay updated on what we're learning about AI and agentic engineering as it happens, we've built a separate AI Fast Track newsletter. Subscribing there brings our latest AI insights to your inbox the moment they're published, piece by piece.

On my desk this week

>> Here's something we were chewing on internally this week: the AI pull request handoff problem.

A teammate created an AI-assisted pull request, then went on holiday. Someone else picked it up and finished it without AI involvement. A critical bug slipped past QA.

What actually broke was the handoff. The original author held a mental model of what the AI had generated and which parts he trusted. None of that was written down. The next person walked in without that context, shipped the work, and the bug landed in production.

If your team is shipping AI-assisted work, two cheap fixes go a long way: label AI-assisted PRs explicitly, and require a short context note on what was generated, what was reviewed by hand, and what's still soft.

The framing that stuck with me: the part that truly deserves praise is the pull request of the plan. The implementation is downstream.

See you in two weeks,

Andreas

Oh, and we have a new website by the way. Happy to hear your feedback.


Recently published articles

The end of the all-you-can-eat buffet
The all-you-can-eat era of AI is ending. Compute constraints, heavier models, and a fully hooked user base are pushing providers toward pay-as-you-go. That shift will force better choices, smaller models, and fiercer competition between tools.
We’re not a normal company
Every software company claims to be different. The “we don’t need X because we have culture” exemption is special pleading. The four phrases that reveal it, and the questions that break them open.
The CTO as prisoner
CTOs who built their company’s survival by doing everything can’t escape that role by scheduling a holiday. Moving from doing to enabling is a skill and identity shift at once. One thing handed off permanently is where the exit starts.
Python as the new Latin
I used to teach people to code. And looking back, I was teaching students to write it by hand while the tools that write it for them were getting better every single month. So what should a coding classroom actually look like now?
Mental capacity is a bottleneck
AI removes bottlenecks until it reaches the one that doesn’t move: human cognition. The faster AI makes your system, the more your team’s mental capacity becomes the constraint. You can’t add more of it.
ElevenLabs: voice cloning, agents, and what they mean for your product
Voice is where AI product differentiation is heading. This post walks through ElevenLabs voice cloning and conversational agents in enough detail to evaluate whether the technology is ready for your use case.

The SaaS Show podcast

Bi-weekly conversations between Sjimi and Andreas on what's actually shaping SaaS right now. Unscripted, under ten minutes. Subscribe on YouTube or Spotify.