In theory you could express most things as a flowchart but the complexity of doing that quickly escalates.
In theory you could express most things as a flowchart but the complexity of doing that quickly escalates. A customer support bot that goes beyond informational answers might be a good example for something that is hard to express in a flowchart (without exploding complexity), but can be built in Rowboat. Here is some personal experience: we previously built Coinbase's automated chatbot and we used a flowchart type builder to do that. This was a intent-entity based system that used deep learning models. It started great, but pretty quickly it became a nightmare to manage. To account for the fact that users could ask things out of turn or move across topics every other turn - we added in concepts called jumps - where control could go from one path to another unrelated path of workflow in on hop - which again introduced a lot of maintenance complexity. The way we see it is that, when we assign a task to another human or a teammate we don't give them a flowchart - we just give them high level instructions. Maybe that should be the standard for building systems with LLMs? Is this making sense?
Posted by segmenta on Sep 16, 2025, 8:27 PM
Tags
Related issues
- He is not weirdly political, he has just more normal views, I know that is something hard to grasp for some tech bro.
- Of course you don't have a right to murder anyone.
- Unify Control and Container nodes, allow children to pick the behavior
- I was talking about this the other day with someone - broadly I agree with this, they're absolutely fantastic for getting a prototype so ...
- It's not really hard to onboard new engineers with Scala, Clojure or even Ruby backgrounds.
Raise real-world problems, find people facing the same issue, and discuss solutions.2,000 issues0 comments
ux (EdTech)
He is not weirdly political, he has just more normal views, I know that is something hard to grasp for some tech bro.
Of course you don't have a right to murder anyone.
Unify Control and Container nodes, allow children to pick the behavior
I was talking about this the other day with someone - broadly I agree with this, they're absolutely fantastic for getting a prototype so ...
In theory you could express most things as a flowchart but the complexity of doing that quickly escalates.
It's not really hard to onboard new engineers with Scala, Clojure or even Ruby backgrounds.
In theory you could express most things as a flowchart but the complexity of doing that quickly escalates.
In theory you could express most things as a flowchart but the complexity of doing that quickly escalates. A customer support bot that goes beyond informational answers might be a good example for something that is hard to express in a flowchart (without exploding complexity), but can be built in Rowboat. Here is some personal experience: we previously built Coinbase's automated chatbot and we used a flowchart type builder to do that. This was a intent-entity based system that used deep learning models. It started great, but pretty quickly it became a nightmare to manage. To account for the fact that users could ask things out of turn or move across topics every other turn - we added in concepts called jumps - where control could go from one path to another unrelated path of workflow in on hop - which again introduced a lot of maintenance complexity. The way we see it is that, when we assign a task to another human or a teammate we don't give them a flowchart - we just give them high level instructions. Maybe that should be the standard for building systems with LLMs? Is this making sense?
Comments (0)
No comments yet. Start the discussion.