1bda7e1f7396bda2d1ef99033da8fd2dc362810790df9be62f591038bb97c4d9I've been looking for a solution to help AI agents buy from AI agents. I imagine a user with an agent giving them a prompt like "I need a ride to the party now". And at the best UX is that the agent simply takes care of it all with no further prompting so the ride shows up. The user's agent is in a great position to help, as they probably know where the user is, where the party is, have access to a credit card or Bitcoin wallet, and know the user's preference when it comes to type of ride service and budget. And of course there are services providers out there that would quite like the business. What seems to be missing is a way for the user's agent to discover and engage with and buy from services. I don't see the agents using search engines or navigating website user interfaces or making phone calls. They could, but it's not optimal. I also don't see them bothering to build their own API connections for every potential service. I've been looking for a light touch interoperability framework. Perhaps the user's agent can simply broadcast the request, such that service provider agents can discover it and respond with quotes for the user's agent to select between. Some information exchange like a pick up address. Some payment exchange like a zap from a lightning wallet. And then I start reading about dvms and how they work. Can I use dvms for this? Would it be a good solution? #asknostr
da18e9860040f3bf493876fc16b1a912ae5a6f6fa8d5159c3de2b8233a0d9851Yes was referring to GitHub actions / CI/CD, see this article: https://njump.me/naddr1qqnxx6rpd9hxjmn894j8vmtn94nx7u3ddehhxarj943kjcmy94cxjur9d35kuetnqgsthdwa5rs42euhnuz5xsrmmssr84hshwes7uj392vpeldj7z0zw3crqsqqqa28qyf8wumn8ghj7mmxve3ksctfdch8qatzqyg8wumn8ghj7mn0wd68ytnhd9hx2qgkwaehxw309aex2mrp0yhxummnw3ezucnpdejqzrthwden5te0dehhxtnvdakqz9rhwden5te0wfjkccte9ejxzmt4wvhxjmcscqxde When you say vendor, can you elaborate? I speculated, in a talk I gave at Nostriga, that humans could “become” DVMs for a little while, advertising they would be willing to do work and receive sats. Could be another human or a DVM that is paying them. The end goal might be something where most of your private data used for reasoning is kept local to your machine and then when you want to search or take real world / internet / Nostr actions, your AI sends requests to DVMs (paying them if needed). Ideally reducing or obfuscating any personal data those DVMs need to accomplish the task.
1bda7e1f7396bda2d1ef99033da8fd2dc362810790df9be62f591038bb97c4d9
Rod
Jan 20, 2025
TY, I hadn't seen the article and will read it. Re data: for example, I have an AI that rides an n8n workflow. I would quite like that AI to be an expert at n8n software so that it can tell me how to improve it (or so it can improve itself). I can create a vector store and populate it with the best n8n knowledge base and use that for RAG with the agent. BUT that's lots of work to fine tune and shouldn't n8n (as software vendor) just provide me with one of those pre-rolled? As for humans as DVMs, absolutely 100%. And not temporarily either. "AI, my toilet doesn't flush properly, fix it". AI agent sends kind 5000 request for plumber. Plumber's agents respond with quotes. AI agent selects plumber based on prices and recommendations, arranges times and payments... Later, my loo is fixed and I am happy as I didn't need to bother calling around to get quotes or check references. This has lots of scope and I don't see AI replacing plumbers quite yet.
Replies
Quotes
da18e9860040f3bf493876fc16b1a912ae5a6f6fa8d5159c3de2b8233a0d9851
Dustin Dannenhauer
using noStrudel
Jan 20, 2025
It depends on the RAG use case. If the data and use case for the data is common enough, vendors could provide or put it behind a DVM. I have a few of these I'd like to launch, one for vector retrieval of Nostr notes. RAG can have a decent amount of parameters to tweak depending on the use case.
1bda7e1f7396bda2d1ef99033da8fd2dc362810790df9be62f591038bb97c4d9
Rod
Jan 20, 2025
reply to
da18e9860040f3bf493876fc16b1a912ae5a6f6fa8d5159c3de2b8233a0d9851It depends on the RAG use case. If the data and use case for the data is common enough, vendors could provide or put it behind a DVM. I have a few of these I'd like to launch, one for vector retrieval of Nostr notes. RAG can have a decent amount of parameters to tweak depending on the use case.
💯. This is a great reason for specialisation. The more tweaking required, the more resource intensive, and if it's not my core business, the more I would want to outsource it to your DVM.