I'm putting together a small group of revenue-share partners for the BusinessAgentCloud platform, and I wanted to open it up here in case it's a fit for you — or for someone you know. How it works The platform runs on workflow templates (four live right now, rolling out as we speak). Every new subscriber gets 5,000 credits free at sign-up — no card, no hardware, no commitment. Depending on the workflow, that's roughly two weeks to a month of free usage, so it's an easy platform to get people onto. The partner side 1) You earn 25% of the revenue from any subscriber you bring in — for life. 2) That covers everything: monthly subscriptions, credit packs, and any future templates or deals they take up. 3) Subscribers are tied to your account, so your share applies to all their current and future spend. 4) You get a dashboard with all your subscribers, their revenue, and monthly stats — and you can reach out to them directly to offer new templates or deals. I've got one partner on board so far and I'm looking to add another two or three. Launch details We launch next week across IE, UK, USA, Canada, Australia and New Zealand, with the partner dashboard (full per-subscriber stats) ready by then. Revenue is paid at the end of each calendar month. Short video introducing the platform: https://youtu.be/o4DOe35Yo14 If you'd like to take part — or you know someone who'd be a good fit — drop a comment below or send me a message, and I'll happily walk you through the details.

I have built an ai receptionist agent in Ireland using ElevenLabs. It makes calls to n8n tools. It is good but I feel some delays when I finish the question up to the point the agent responds. I use the widget not connected to a number yet. Is there a way to avoid this delay? Are VAPI or Retell better in term of delays? Thanks Shadi

I need to build a chatbot to lead people to use an app, the app has some pretty complicated features. I need to use local AI for privacy. I need to use RAG for user manuals and educational videos. Thinking of model like Llama 3.1 8B and some other local models for transcribing and embedding. Do you think such models, particularly Llama 3.1 8B and the available small embedding models can perform well in handling conversation to lead users to configure a relatively complex app? Would Llama 3.1 8B follow strictly a complex system prompt and make a correct usage of tools? Any other SLMs can handle this well? What about small embedding models? Anything about small transcribing models? Regards Shadi Ghaith

Hi Guys I have built an AI Receptionist that I plan to sell to medical services in Ireland. I have collected 100's of phones and I plan to be making calls myself to try to book demos. As there are many leads, I'm thinking of the feasibility of making AI to call leads via phone and try to book demo meetings. If anybody tried this, can you comment on the results of such campaigns? Would people be willing to book demos and even take things seriously if they realize they are talking to AI? Anybody can comment on the ratio of calls to demo meeting booked? And how many end up attending such demo calls? Given there are many leads, does it make sense to do actual calls for the highest quality leads and do AI calls with the moderate quality leads? Also can any body comment on the cost and hence the ROI of such campaigns? Regards Shadi Ghaith

Hi I have built a scheduling and answering workflow with ElevenLabs and n8n. I developed n8n calendar workflows (no AI) in n8n and made them available via webhooks as tools to ElevenLabs. The ElevenLabs system prompt provides all the details to the ElevenLabs LLM (using Gemini 2.5 Flash). This is working well but sometimes I feel that I can do with a stronger model like Gemini 2.5 Pro but it is not available and likely to be slow. Also I notice delays in responding while making multiple tool calls. I'm thinking if my approach is the best approach, particularly I wonder if it is going to be better to make an orchestration agent at n8n that has the same n8n tools but to be utilized as sub workflows (no ai) instead of webhooks. In this approach the main system prompt will be at the n8n agent and it will make quick tool calls locally. In this approach the LLM at ElevenLabs will handle the discussions with the user via voice and delegates most requests to the n8n orchestration agent (via webhook). Hence I can use very strong model at the n8n side and tool calls will be faster. The ElevenLabs system prompt will be much simpler. I still didn't try this but I wonder if anybody has a preference on which approach to go? The current approach to allow ElevenLabs to access remote tools individually, while the proposed approach will mean calling a remote agent for almost everything but that agent can have faster access to local tools. The n8n agent may need to ask for extra information which would be slow in this case. My goal of the proposed change will be to both have a stronger LLM and reduce multiple remote tool calls and so reduce delays. Any ideas? Regards Shadi Ghaith