Multi-Agent on Lynx Tech Blog

After 100 Logos: A Postmortem of the Third Wave in Exhaustive Brand Exploration

Mon, 24 Aug 2026 09:00:00 +0800

Goal: One Hundred Comparable Candidates After the first two batches, there were 28 directions on the comparison board. This round’s goal was much more ambitious: fill the board with one hundred usable logo candidates and lay them all out so I could pick through them one by one. “Usable” and “padding the numbers” are two entirely different things. The lessons from the first two batches were clear enough: the agent reviewer only checked path coordinates, not actual re

13 AI Company Logo Directions That Aren't Lynxes: A Retrospective on a Multi-Agent Brand Exploration

Sun, 23 Aug 2026 20:30:00 +0800

A Quirky Problem: The Lynx in My Domain, But I’m Not a Cat Person My personal domain is lxlynx.com, and every product under it carries the Lynx prefix—LynxFlow, LynxPipe, LynxAct. By the usual playbook, the brand logo should depict a lynx: a feline with two iconic tufts of black fur on its ear tips, highly recognizable, a favorite motif for logo designers.

Managing AI agents in the terminal: I ended up keeping herdr — a head-to-head review of four managers

Tue, 11 Aug 2026 00:00:00 +0800

Prologue: First, Getting Tangled Up by My Own Pile of AI Agents My recent workflow has turned into this: several AI agents running in the terminal at the same time—Claude Code modifying one project, Codex doing research in another, and yet another one generating content. Multiple projects in parallel, with the terminal as the main arena. Then came the problem: I had no idea which agent was stuck, what it was waiting for, or whether it had finished. I tried tmux, used it for a while, then dropped