Edgecaser LLC logo

Blog

Writing on product judgment, AI trust boundaries, and the operating decisions in front of founder-led teams. Newest first.

Your product needs a return reason before it needs rewards
July 2026 · 5 min read

Streaks and push alerts can prompt another visit. They cannot make a static product useful twice.

Before you hire a Head of Product, shrink the AI surface area
July 2026 · 5 min read

AI can make a small team look larger than it is. The hard part is deciding which promises the product should own before a permanent product leader is worth hiring.

Put AI trust gates in the product spec before launch
July 2026 · 5 min read

A working demo proves the model answered once. The spec has to explain what users should trust, review, or ignore when the next answer is partial, stale, or wrong.

Compositor: building my own book and audiobook production suite
May 2026 · 8 min read

Two months of evenings, four stages, three thousand lines of Python: what I learned building a multi-voice audiobook pipeline for my novel Cold Storage.

I Built a Conflict Harness to Compare Claude and GPT. The Hardest Part Was Trusting the Judge.
April 2026 · 16 min read

I built a harness to compare Claude and GPT on real PM scenarios, then used swap-testing to separate real quality differences from judge bias.

When LLMs Judge LLMs, Who Judges the Judges?
April 2026 · 8 min read

I set out to build a harness that would let an AI act as a neutral judge. The tricky part was realizing the judge wasn't actually neutral.