[Question] Context: Solar client using Assistable for lead qualification and appointments. Requirement: Agent needs comprehensive understanding of all 5 services and related products to be able to respond to client enquiries and provide product and service details to move the deal forward. Challenge/Ask: So far the client has sent me around 10 documents just to cover their services. The still need to send me way more. I estimate there will be 30+ pages of knowledge I need to make available to the AI agent. I considered creating 5 specialist agents, but I feel the complexity will be too much and would prefer 1 agent with a basic task based prompt making use of custom fields to determine the lead enquiry type (Boiler, Solar etc). Question: Does Assistable have a limit on the size of the Knowledge Base? Can I create a comprehensive KB using the Q&A vector method to manage 30+ pages of information? What would be best practice? Any guidance and assistance would be greatly appreciated. Colin

**This post is for the technical builders** For those who dont use tooling -- its the actual key for enterprise use cases and its the biggest differentiator, even internally, as you chase big projects / clients. We have set up abilities using tools, middleware and external database that you wouldn't even believe and they are very high ticket (think north of $50k), I suggest its something to take a look at if you haven't before So, as we build alongside you for fulfillment we noticed some limitations that I think needed to be addressed. So, here is the basis of those additional functionalities: post / put / patch / get / delete, execution type (proxy, direct, workflow execution), headers, timeout MS, flattened tool menu to a page not a popup Proxied tool calls is your traditional tool call for middleware as you see it today. Output is wrapped in an args object with a meta_data object. These are best suited for middleware usage (make, n8n, buildship, etc) because not only do you have your agent's output but you have location id, contact id, etc. Direct tool calls are exactly that - we dont wrap it in anything - we just send the raw request exactly as you have configured it. This is for when you want to attach to something like an MLS, or niche API directly. Cofigure headers (variable friendly), configure body parameters (and soon query parameters), and the http type. We'll send the request on your behalf just as you would anywhere and return the direct output. Workflow execution is for the internal workflow engine we are adding so we can supply you with a middleware if you dont already have one, or looking for something more native to our functinoality. more to come, happy thursday

I'm looking for a solution that allows me to connect with an existing WhatsApp number (from Columbia). Which option do you recommend? - GHL Native Connection - WAGHL - AppLevel WhatsApp - Would love to hear your experiences! Drop your thoughts below. 👇

Anybody have any videos on how to actually use this? Trying to wrap my head around it and take my bots to the next level.