kinda surprising to see basically just LLM wrappers still getting funded/interest. Neat idea obviously and nice to have, but that's sort of it. Fundamentally misses mark on what you can do already without AI (running tests on your actual doc code examples etc), and fact that any of the AI IDEs could turn part of this one with single switch to just append a doc friendly update to a commit. To think that soon we have a…
Launch HN: Promptless (YC W25) – Automatic updates for customer-facing docs
51–60 of 62 posts
Re: Launch HN: Promptless (YC W25) – Automatic updates for customer-facing docs
#52Very real problem. We have started to worry about how to maintain the many cookbook samples and tutorials, we wrote/are planning on writing. Going over every user facing artefact after a code change is a non-starter, so you opt for versioning these things as they'll necessary become out of date. Very excited to give this a spin soon.
Re: Launch HN: Promptless (YC W25) – Automatic updates for customer-facing docs
#53Re: Launch HN: Promptless (YC W25) – Automatic updates for customer-facing docs
#54Very real problem. We have started to worry about how to maintain the many cookbook samples and tutorials, we wrote/are planning on writing. Going over every user facing artefact after a code change is a non-starter, so you opt for versioning these things as they'll necessary become out of date. Very excited to give this a spin soon.
Even OpenAI's cookbook is out of date in many places. This is a really difficult and common problem!
Re: Launch HN: Promptless (YC W25) – Automatic updates for customer-facing docs
#55Congratulations on Launch
Re: Launch HN: Promptless (YC W25) – Automatic updates for customer-facing docs
#56This idea is cool and well-scoped to a specific pain point that can be solved today. This is something that I think we need more of when it comes to YC batches. However, you all should publish pricing before launching, and forcing me to book a call with you to use it is a nonstarter for me. I don't want to get tied to this tool and then be charged for it in some weird way; give me your v0 pricing so that I can pay fo…
Yeah, this is very valid. We opened up a self-service trial this week so that people can more easily give it a spin before deciding to join a paid plan, but we're still working on a lot of the customer experience things to offer a truly complete onboarding experience. Appreciate the feedback!
Re: Launch HN: Promptless (YC W25) – Automatic updates for customer-facing docs
#57Can you clarify the slack integration? I see you've mentioned it, but I'm unclear on the workflow.
A use-case I've thought about previously is support discussions we have on our slack channel, which indicate that we need to update our docs.
Is Promptless able to raise a PR with suggested updates on docs, based on question/answers in our support channels?
Re: Launch HN: Promptless (YC W25) – Automatic updates for customer-facing docs
#58Looks great - well done! Can you clarify the slack integration? I see you've mentioned it, but I'm unclear on the workflow. A use-case I've thought about previously is support discussions we have on our slack channel, which indicate that we need to update our docs. Is Promptless able to raise a PR with suggested updates on docs, based on question/answers in our support channels?
Here's a video we made a month or so ago that shows how (1) works, hope that helps! https://www.tella.tv/video/cm5x8uj9f001d0al11vyxcnsc/view
Re: Launch HN: Promptless (YC W25) – Automatic updates for customer-facing docs
#59Re: Launch HN: Promptless (YC W25) – Automatic updates for customer-facing docs
#60kinda surprising to see basically just LLM wrappers still getting funded/interest. Neat idea obviously and nice to have, but that's sort of it. Fundamentally misses mark on what you can do already without AI (running tests on your actual doc code examples etc), and fact that any of the AI IDEs could turn part of this one with single switch to just append a doc friendly update to a commit. To think that soon we have a…
Ironically, the common (used to be common?) trope about foundation models being picks and shovels and LLM wrappers having no values is probably backwards. ChatGPT is the most valuable AI product and it's just a wrapper around an underlying LLM that is not 10x better than the rest of the models.