Short observations from building systems, working with AI and shipping in public.
21 entries · One idea at a time · Updated Aug 6, 2026
The content pipeline behind my daughter's story brand runs on a single MacBook. Local image generation, local TTS, local orchestration. Clou...
para-radar collects Turkish lira yield opportunities: money market funds, deposit campaigns, daily interest accounts. It compares everything...
I run an autonomous agent that posts market commentary to X. Before it was allowed to publish anything, it ran for weeks in shadow mode: ful...
dogrubakar.com lived on free Yandex mail for years, until it went read-only behind a paywall. The move to Google Workspace had one hard requ...
I did not want three review agents for three CLIs. I wanted the agent I already tuned for Claude Code to run everywhere. That one constraint...
multi-agent's arena ends with a scoreboard: which model found real bugs, which one hallucinated, which one conceded gracefully. The design d...
The first version of multi-agent's arena ran a fixed number of rounds. Three models, four rounds, every time. Half of those rounds were thea...
The lazy way to move context between two coding agents is to copy the whole conversation. It is also the wrong way. A transcript is large, i...
The worst bug in context-bridge was not in my code. Every handoff reported success and carried an empty delta. Claude Code, Codex and Grok k...