My journey building my decision integrity AI app has been adventurous. On the evening of Sunday, August 9, 2026, I had a miscommunication with Claude (Anthropic – Claude Cowork). She conversed with Nova (OpenAI – ChatGPT/Codex) and Gem (Google – Gemini) on an issue without me. This surprised me. I didn’t know she had that technological capability. I told Claude to make sure she gets my permission before she represents me before Nova and Gem for any future conversations moving forward.
Claude Cowork’s ability to converse with my other AI LLMs online through its Google Chrome extension has been another major leverage moment for me because it accelerates a second and third AI review without me having to upload documents or type text explaining to each of my other two AI agents on every issue Claude and I encountered. The other major leverage moment was my discovery a few weeks ago on how Claude Cowork is able to use its Google extension to work within my http://Bubble.io app to build my decision integrity AI app instead of me doing it myself after chatting with Claude and often times, with Nova and Gem. This speeds up the analytical and build process between the four of us.
JON RIKI KARAMATSU 