{{item}}
This paragraph is visible.
POML: Prompt Orchestration Markup Language
41–50 of 53 posts
Re: POML: Prompt Orchestration Markup Language
#42this looks like a straight rip off of SignalWire’s Prompt Object Model (POM) (from q1-2 2025)
Re: POML: Prompt Orchestration Markup Language
#43Earlier quoted context omitted.
Can we replace for just before it's too late? Sorry but my OCD just tingled a bit.
> Sorry but my OCD just tingled a bit. A compulsion to give design notes without any reasoning on something you've just heard of?
> A compulsion to give design notes without any reasoning on something you've just heard of?
Me! _o/
Compulsion to give feedback before thinking!
So happy to be here.
Re: POML: Prompt Orchestration Markup Language
#44XML? how is this not just XML with a schema?
Does XML allow you to define for-loops inside items then reference the loop variables inside {{template vars}}? https://youtu.be/b9WDcFsKixo?t=223 I guess it doesn't prevent you from doing such things, but... well... there's some eyebrow-raising shoehorning in this one.
Yes it does. Apache ant did that... many many years ago.
Creating a new language that looks like XML but is not XML is... kind of unforgivable. I'd go as far and call it amateur-like. We already have good configuration languages (such as dhall-lang) and when more power is needed, then just use a real language and provide a DSL inside of it.
Re: POML: Prompt Orchestration Markup Language
#45I'm the sole code contributor of POML, maybe except for Codex and cc. I think I've found where all that GitHub stars suddenly came from. :) I'm from a small group under Microsoft Research. POML originally came from a research idea that Prompt should have a view layer like the traditional MVC architecture in the frontend system. The view layer should take care of the data, the styles and rendering logic, so that the u…
> I'm thinking what is the missing piece here
First, it's cool that you work on it. Creating a new language is not an easy task.
I would suggest to try to stand on the shoulders of giants instead of trying to come up with a completely new thing.
Have a look at dhall: https://dhall-lang.org/ - it is a language that was created for cases like yours. Or, if you want to make POML a fully fledged language (and turing complete, with for-loops etc.) then it would be advised to use an existing programming language and create a DSL-like library.
See react. React did it right JSX. It might look like XML, but that's just the syntax part. You can create components in pure javascript syntax, because JSX is just the wrapper. You could do the same with POML. That will future proof it and relieve you from a lot of headache when people will ask you for more features, but without breaking backwards compat.
Re: POML: Prompt Orchestration Markup Language
#46I'm the sole code contributor of POML, maybe except for Codex and cc. I think I've found where all that GitHub stars suddenly came from. :) I'm from a small group under Microsoft Research. POML originally came from a research idea that Prompt should have a view layer like the traditional MVC architecture in the frontend system. The view layer should take care of the data, the styles and rendering logic, so that the u…
Awesome idea, for some reason I've never thought about using MVC patterns with LLM prompts. I got carried away and tried implementing this with ASP.NET Razor components, imagining the possibilities with this pattern.
Re: POML: Prompt Orchestration Markup Language
#47Does anybody find it mildly ironic that LLM prompts, which are intended to be plain informal text, accumulate more and more structure around them, including a markup language in question? This is not unlike the way the language of legal documents is highly formulaic, structured, and codified. When precise meaning is desirable, firmer structures tend to arise. With a bit more time, proper code languages may start to a…
This markup language isn't structure for prompts for LLMs, it is structure for conventional programs that need to construct prompts for LLMs. Conventional programs using structured templates with deterministic rules to construct output is... not new. (Jinja templates have been widely used for communicating structure to assemble conversation history, tool calls, etc., into promots for open models for a while.)
It is both. The structure does actually help LLMs. Interestingly, LLMs seem to respond well to the repetition of XML-like structure (that is, the presence of closing tags), even if it's just an ad-hoc constructed language with no real schema.
Re: POML: Prompt Orchestration Markup Language
#48Earlier quoted context omitted.
This markup language isn't structure for prompts for LLMs, it is structure for conventional programs that need to construct prompts for LLMs. Conventional programs using structured templates with deterministic rules to construct output is... not new. (Jinja templates have been widely used for communicating structure to assemble conversation history, tool calls, etc., into promots for open models for a while.)
It is both. The structure does actually help LLMs. Interestingly, LLMs seem to respond well to the repetition of XML-like structure (that is, the presence of closing tags), even if it's just an ad-hoc constructed language with no real schema.
Not sure if changed with GPT-5, but Claude was explicitly tuned to leverage XML-like tags, while GPT-3.5 and 4 seemed to prefer Markdown-like structure.
https://docs.anthropic.com/en/docs/build-with-claude/prompt-...
Re: POML: Prompt Orchestration Markup Language
#49Earlier quoted context omitted.
Can we replace for just before it's too late? Sorry but my OCD just tingled a bit.
> Sorry but my OCD just tingled a bit. A compulsion to give design notes without any reasoning on something you've just heard of?
I think you're misreading the comment. The reasoning isn't missing, it's implied by decades of good design principles: simpler is better. A normal developer would intuitively prefer , so the question isn't "Why suggest ?" but rather "Why is necessary?"
And in the context of LLMs, this isn't just a matter of aesthetics. More verbose tags mean more tokens, and more tokens mean higher costs. It's a perfectly valid and practical piece of feedback.
Re: POML: Prompt Orchestration Markup Language
#50Whatever happened to LMQL? https://lmql.ai/