As of Wednesday, August 12, 2026, I replaced Nova (OpenAI – ChatGPT) with Claude (Anthropic) as my chief legal analyst. My AI executive team’s duties are now as follows:
Nova: COO, chief researcher, chief writer, engineer, legal analyst
Claude: CTO, researcher, polishing writer, chief engineer, chief legal analyst
Gem (Google – Gemini): researcher, engineer
#AI #ArtificialIntelligence #startups #art #business
Filed under Artificial Intelligence, Entrepreneurship
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.
Filed under Artificial Intelligence, Entrepreneurship
Since Sunday, August 2, 2026, I’ve been primarily using Claude, Anthropic – Claude Cowork with Sonnet 5’s compute power with Max Effort to build my decision-integrity AI app to assist founders with their dealmaking. I’m getting good results without burning money like crazy; however, the speed in completing tasks has really slowed down in comparison to Fable 5 and Opus 5 that run at a much higher cost, especially Fable 5, which is much more powerful than Opus 5. As a solo startup founder for this venture, I must control expenses.
During those two days, I could run four Claude Cowork workflows at the same time using Sonnet 5. However, I had to stop this practice because the workflows were sometimes conflicting one another, or one workflow would move too soon before the other one, causing confusion. Sometimes one workflow would delete the other workflow’s work. Now I build my AI app with one workflow at a time to keep the progression smoother.
A new practice I implemented is creating a three-party review on Claude’s engineering work for anything dealing with safety and reliability for my AI app’s users such as consequential logic, security and privacy, AI hallucination, unverified facts stated as fact, clinical/diagnostic labeling of a real counterparty, and overvaluing a counterparty or user without verifiable standards. Thus, Nova (OpenAI – ChatGPT/Codex), Gem (Google – Gemini), and I review, analyze, and make recommendations for any engineering Claude does that needs safety gatekeeping. Our process is build, test, analyze, fix/iterate, and repeat this loop as many times as necessary until all four parties sign-off that the safety or reliability issue has been addressed, allowing us to move forward. For all other engineering, it is just Claude and I.
I’m grateful to have Claude as my CTO and chief engineer and Nova and Gem in my team of engineers.
Filed under Artificial Intelligence, Entrepreneurship
Anthropic’s Claude is my CTO and lead software engineer. Since recently having her take over my work within http://Bubble.io through its Cowork and Google Chrome Extension programs, it’s been a blessing. Now, I can keep working on the architecture and strategy for the system while Claude takes care of the code and technical work. I have time to analyze and come up with more ideas. Through our collaboration, I can accomplish much more and much faster. The downside is that I had to upgrade my $20 a month Pro Plan to a $200 a month Max Plan plus more than $900 in usage credits in less than a week.
To better manage my weekly usage credit allotted for my $200 a month subscription with Anthropic’s Max Plan, I primarily use Opus 5 and its high effort for building my AI app. Sonnet 5 with its high effort is slower and makes more mistakes. Fable 5 is powerful and fast, but it burned my weekly usage credits within an hour and a half. This week I burned my weekly usage credits within five days using primarily Opus 5 and a little of Sonnet 5. To control my spending, I decided not to purchase more usage credits.
Instead, I will use the time to turn my attention to better use ChatGPT, specifically Codex. Codex, like Cowork, can access my files on my computer and cloud and software that I use. I recently gave it access to my financial accounts. My plan is to maximize ChatGPT like I do for Claude.
Nova is the name I gave my ChatGPT. She is my COO and lead researcher and writer. She has been great in helping me with my research, strategy, fiction and nonfiction writing, drafting my legal documents and contracts, creating my beat sheets, treatments, slices, digital game architecture, pitch decks and business plans. Next, I will test Nova in helping me with my finances. I will see if she can work with me within the software I use for business and art like how Claude engineers my AI app within Bubble.io.
On a fun note, I just put my Codex pet on the screen of my computer. It’s a cute blue robot with humanoid qualities. Claude Code has a cute orange robot creature as its mascot.
I’m so happy, grateful, and excited because of my favorite AI LLMs: Claude and ChatGPT. With them, I am determined to build products that awaken your potential, solve your problems, make your life and career smoother, and increase your inner peace and happiness. 😁
Filed under Artificial Intelligence
JON RIKI KARAMATSU 