Automatically mine and create agents for any business. Over the weekend I went to the Google IO hackathon and had a blast building what I called Mitosis.
Generates a synthetic company to create conversations and people, automatically extract the workflows from the company based on the conversations and build out new agents to automate the busy work.
Pushes all context into the company brain, leverages governance and policy gating to make sure the right person stays in the loop and the agents learn from their mistakes as they make them to get better over time.
The end result is a 95% drop off of handoff between the employees in this example. Each week the agents can take on more to empower the employee to get even more work done while making the important judgement calls.
This is all of course synthetic and the milege will vary greatly per company and workflows but was a great experiment to build in a day and leverage a lot of the work I have been working on for other businesses. It was also great to try out the antigravity managed agents and Gemini 3.5 Flash.
In this demo you may see that it is listed as mock, this is definitely mocked. In the hackathon we had an account with free credits. I burned through the rate limits and the credits rather quickly. The rate limit for the anitgravity agents was 200k a minute, I blew past it at 2M a minute. So this was definitely tokenmaxxing.
I look forward to expanding this further to other platforms and technology partners but was a blast to build.
Doesn’t that just tell you directly how to cheat the system again? Just pass in those rules or make a skill to “humanize” the text. People hate writing memos that is why people are having ChatGPT write it. Also maybe install a company brain and agents to communicate all of these pieces instead of having people bother with it at all and just have an artifact that you can ingest if you need to.
This is quite impressive! I wonder if this will cause other folks to follow suite. Maybe have an insured offering for a bit higher than the base API price?
Spoke to some top engineers at top companies who are “tokenmaxxing” and let’s just say they would definitely be getting a refund.
AI should earn its keep. Introducing the AI Productivity Guarantee.
If Devin delivers less engineering value than you’re paying for, Cognition will fund your usage until it does, up to $10 million.
It’s time for the AI industry to stop maximizing tokens and start maximizing productive output.
@adilmania I still don’t get why this can’t just be an update on my iPhone or let your agent of choice have all of the connections to your apps and do it all through hosted MCP outside of Apple
Leading companies are moving from two-week sprint cycles to a daily rhythm that combines human judgment with overnight agent execution.
The opportunity now is how organizations use the capacity those agent-enabled workflows create. https://t.co/heERvijLRD
@DanielMiessler Do you think we could ever live in a world where cached reasoning could act like chunks of code? It’s something I’ve thought about for a while
Opus 4.8 landed right after I posted this, and it makes the Mitosis idea feel way more real: mine the messy conversations, find the repeatable work, and turn it into governed agents. Not chatbot for everything - managed AI labor with humans still making the calls.
Automatically mine and create agents for any business. Over the weekend I went to the Google IO hackathon and had a blast building what I called Mitosis.
Generates a synthetic company to create conversations and people, automatically extract the workflows from the company based on the conversations and build out new agents to automate the busy work.
Pushes all context into the company brain, leverages governance and policy gating to make sure the right person stays in the loop and the agents learn from their mistakes as they make them to get better over time.
The end result is a 95% drop off of handoff between the employees in this example. Each week the agents can take on more to empower the employee to get even more work done while making the important judgement calls.
This is all of course synthetic and the milege will vary greatly per company and workflows but was a great experiment to build in a day and leverage a lot of the work I have been working on for other businesses. It was also great to try out the antigravity managed agents and Gemini 3.5 Flash.
In this demo you may see that it is listed as mock, this is definitely mocked. In the hackathon we had an account with free credits. I burned through the rate limits and the credits rather quickly. The rate limit for the anitgravity agents was 200k a minute, I blew past it at 2M a minute. So this was definitely tokenmaxxing.
I look forward to expanding this further to other platforms and technology partners but was a blast to build.
@stripe@marclou@Pauline_Cx@fatimarizwan "If you want to go fast, go alone. If you want to go far, go together." Now with AI the right person can go much farther than before but just as fast. They will still need to get a team in the future tho
@elonmusk Honestly I think a lot of people are sleeping on Grok. The performance is great but the pricing is crazy cheap. Definitely best bang for your buck