Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Flow – A dynamic task engine for building AI agents

github.com

Post reply on HN
Print view View original

31–40 of 53 posts

Re: Show HN: Flow – A dynamic task engine for building AI agents

#31

Post by hatefulmoron »

skull8888888 wrote: post #13
fidotron wrote: post #8

I tend to agree the graph approach is wrong. I have a meta question though - there seems to be a huge amount of activity in this space of LLM agent related developer tooling. Are people actually successfully and reliably delivering services which use LLMs? (Meaning services which are not just themselves exposing LLMs or chat style interfaces). It seems like 18 months ago people were running around terrified, but now…

My main company is Laminar ( https://www.lmnr.ai ) and we actually help folks ship reliable LLM software to prod. We've seen many of our clients successfully do that. Although, the entire space is very new for sure and things are changing everyday

What kind of stuff are people doing? I understand if you don't want to be too specific, but do you have any interesting (vague) examples using agents that aren't in the chat bot space?

Re: Show HN: Flow – A dynamic task engine for building AI agents

#32

Post by throwaway314155 »

bosky101 wrote: post #27

Why limit yourself to AI and agents? seems abstract enough that tasks, and parallel execution could be anything Moreover, there isn't an example how it `could` work for inference or function_calls/tools/agents But looks simple to get started and feels like it has the right foundation for good things to come. Kudos!

Agreed. It seems like this has nothing to do with agents. In particular because this is well trodden territory that frameworks like Airflow have been tackling since _well_ before the recent deep learning craze.

I would say that unless agent based examples are highly compelling, it makes more sense to simply remove the agent stuff completely from the pitch, lest you be inevitably accused of taking advantage of the current AI hype for an otherwise unrelated piece of technology (that happens to be a good fit for agent based workflows - something which I haven't observed to even work very well with the best models).

Re: Show HN: Flow – A dynamic task engine for building AI agents

#33

Post by skull8888888 »

hatefulmoron wrote: post #31
skull8888888 wrote: post #13

Earlier quoted context omitted.

My main company is Laminar ( https://www.lmnr.ai ) and we actually help folks ship reliable LLM software to prod. We've seen many of our clients successfully do that. Although, the entire space is very new for sure and things are changing everyday

What kind of stuff are people doing? I understand if you don't want to be too specific, but do you have any interesting (vague) examples using agents that aren't in the chat bot space?

- AI auditor of Otel traces - wealth manager advisor - AI data engineer to name most interesting cases without giving too much details

but also many chat bots and assistants too

Re: Show HN: Flow – A dynamic task engine for building AI agents

#34

Post by skull8888888 »

uptownfunk wrote: post #29
skull8888888 wrote: post #26

Earlier quoted context omitted.

Noted. I had no intention to be disrespectful in any sense. Just pointing out flaws and reasons why and how current project came to be.

Not talking about you!

oh, got it :)

Re: Show HN: Flow – A dynamic task engine for building AI agents

#35

Post by skull8888888 »

throwaway314155 wrote: post #32
bosky101 wrote: post #27

Why limit yourself to AI and agents? seems abstract enough that tasks, and parallel execution could be anything Moreover, there isn't an example how it `could` work for inference or function_calls/tools/agents But looks simple to get started and feels like it has the right foundation for good things to come. Kudos!

Agreed. It seems like this has nothing to do with agents. In particular because this is well trodden territory that frameworks like Airflow have been tackling since _well_ before the recent deep learning craze. I would say that unless agent based examples are highly compelling, it makes more sense to simply remove the agent stuff completely from the pitch, lest you be inevitably accused of taking advantage of the cur…

For me Agent is essentially a decision making machine. I had many iterations on the software around building agents and Flow is the culmination of all of the learnings.

For some reason some LLM specific examples just slipped of my mind because I really wanted to show the barebone nature of this engine and how powerful it is despite its simplicity.

But you also right, it's general enough that you can build any task based system or rebuild complex system with task architecture with Flow.

Signal is clear, add more agent specific examples.

Re: Show HN: Flow – A dynamic task engine for building AI agents

#36

Post by potamic »

uptownfunk wrote: post #25

PSA: It’s really rude when someone does a show HN to go and plug your own competitor. Let them have their moment

I kinda disagree. This is a discussion forum first, advertising should just be a side effect. Anyone posting here should do with an intention to spark discussions and elicit greater wisdom of the community. And if that wisdom happens to be comparisons to prior art, so be it. I don't think it should take away anything from the work, but only expand both the author's as well as the community's awareness on the topic.

Re: Show HN: Flow – A dynamic task engine for building AI agents

#37

Post by j45 »

sprobertson wrote: post #2

I agree complex conditional LangGraph setups get pretty tedious after a certain point - though you claim to not use graphs here, but isn't that essentially what returning the "next task" does? The graph isn't explicitly defined but it still exists implicitly if you trace through all the tasks and next tasks. Would be interesting to see a complex agent implementation in both Flow and regular LangGraph to compare maint…

Sometimes it reminds me of the evolution of process management software.

What might be new to those developing tooling with AI, might not be new to other areas of software.

Re: Show HN: Flow – A dynamic task engine for building AI agents

#38

Post by krawczstef »

Interesting! I feel like this is a cross between https://github.com/dagworks-inc/burr (switch state for context) and https://github.com/Netflix/metaflow because the output of the "task" declares its next hop...

The challenge with this approach though is that you need to run the actual code to see what it does, or as a developer build up a mental model of the code ... but it does shine in certain use cases -- and also reminds me of https://github.com/insitro/redun because it takes this approach too.

Re: Show HN: Flow – A dynamic task engine for building AI agents

#39

Post by skull8888888 »

krawczstef wrote: post #38

Interesting! I feel like this is a cross between https://github.com/dagworks-inc/burr (switch state for context) and https://github.com/Netflix/metaflow because the output of the "task" declares its next hop... The challenge with this approach though is that you need to run the actual code to see what it does, or as a developer build up a mental model of the code ... but it does shine in certain use cases -- and also…

burr looks very interesting!

Re: Show HN: Flow – A dynamic task engine for building AI agents

#40

Post by jimmySixDOF »

krawczstef wrote: post #38

Interesting! I feel like this is a cross between https://github.com/dagworks-inc/burr (switch state for context) and https://github.com/Netflix/metaflow because the output of the "task" declares its next hop... The challenge with this approach though is that you need to run the actual code to see what it does, or as a developer build up a mental model of the code ... but it does shine in certain use cases -- and also…

...also MemGPT (now called Letta) https://github.com/letta-ai/letta
Post reply on HN