Our renewals AI solution, announced yesterday, is set to help brokers accomplish 12-hours of work in an 8-hour workday.
@Will_Johnson sits down with @Machiz and @clairejyz to discuss how we built this and what it means for today's brokers.
Full video: https://t.co/lIXnXxzlPz
“Look at my incredible new factory!”
Yo that’s cool, what do you make?
“It’s highly optimised, fully automated, zero tolerance for defects and with a continuous feedback cycle”
Cool cool, so what do you actually make?
“I can interact with it on my phone, laptop, messenger, completely async, and the shared context means it’s always learning how to get better”
Very impressive, but what do you make?
“Every agent has full context, can spawn other agents, review their work, fix defects, and ship continuously.”
yes yes. WHAT DOES IT MAKE?
“Software.”
Oh nice. What software?
“Well right now we’re mostly using it to improve the factory.”
Improve it to make what?
“Anything!”
Such as?
“…a better factory.”
Now in beta: Notion as code.
Define an entire workspace in TypeScript: teamspaces, databases, custom agents, all of it… then deploy it through the API.
Build workspaces with coding agents, version-control your setup in git, and reproduce the same setup anywhere you need it.
old but wise rule: don’t standardize early. emerging version: premature standardization is still worse than a little duplication. but stay consistent obsessively, because the reader you’re optimizing for changed. humans tolerate inconsistency better than models do.
seems obvious but:
things that are changing rapidly:
1. context windows
2. intelligence / ability to reason within context
3. performance on any given benchmark
4. cost per token
things that are not changing much:
1. humans
2. human behavior, preferences, affinities
3. tools, integrations, infrastructure
4. single core cpu performance
therefore,
ngmi:
1. "i found this method to cut 15% context"
2. "our method improves retrieval performance 10% by using hybrid search"
3. "our finetuned model is cheaper than opus at this benchmark"
4. "our harness does this better because we invented this multi agent system"
5. "we're building a memory system"
6. "context graphs"
7. "we trained an in house specialized rl model to improve task performance in X benchmark at Y% cost reduction"
wagmi:
1. product/ui
3. customer acquisition
4. integrations
5. fast linting, ci, skills, feedback for agents
6. background agent infra to parallelize more work
7. speed up your agent verification loops
8. training your users, connecting to their systems and working with their data, meeting them where they are
https://t.co/hB1r7yxmGU
imho, “beginner’s mind” can be an advantage. Fewer assumptions, less attachment to old tools, more willingness to rethink the workflow. “No coding experience” is not the same thing.
My brother is a civil engineer. He found Claude and now I get a new CNAME request every day for some internal tool he built for his biz.
That’s the tell. AI makes custom software viable in places it never was before. The surface area for software just got much bigger.
Microservices without scale is just distributed monolith cosplay. People reach for network boundaries when what they actually need is better domain modeling.
Overused.
https://t.co/4AUYHA7QKi