I'm building a WhatsApp AI agent using Claude API + Make. I need Claude to ALWAYS return a specific JSON structure using tool use / function calling. Has anyone successfully implemented Claude tool use in Make's HTTP module? What does your request body look like? How do you handle the response parsing? Does anyone use Make's native Anthropic Claude module vs the HTTP module for Claude API calls? Which is more reliable?

Appreciate everyone who’s been helping on my last posts — the insights have been super helpful. I’m newer to Apollo, but from what I’m hearing it seems like one of the best tools for cold email, which is what I’m focusing on for my cleaning company. Right now I’m targeting:• Property managers• Office / facility managers• Law firms / professional offices Basically anyone in a position where they control a budget and need recurring cleaning. I started testing small batches of emails through Apollo, but I’m running into an issue where a lot of the emails don’t seem to be valid or just don’t get responses. For those doing this consistently:How are you finding accurate, responsive contacts? Are you relying fully on Apollo, or combining it with other tools / methods/linkedin? My goal is pretty simple:Lock in 20–30 solid commercial leads per month and turn those into walkthroughs. Would really appreciate how you guys are approaching:• finding the right decision-makers• getting valid emails• improving response rates Trying to dial this in the right way from the start.

I run a residential and commercial cleaning company and have been experimenting with using AI + automation for LinkedIn. The idea right now is: Find property managers, office managers, realtors, and facility managers on LinkedIn• Use automation to build targeted lead lists• Use AI to generate posts about cleaning, property management, and maintenance tips• Schedule posts automatically to stay consistent• Convert engagement and DMs into walkthroughs and cleaning contracts Basically trying to turn LinkedIn into a consistent B2B lead channel instead of just posting randomly. For people here automating LinkedIn: What tools or workflows are working best for you? Are you doing something likeClaude → n8n → scheduled LinkedIn posts or using something else entirely? Curious what systems people are running.

I'm 21 and started my own AI automation agency 2 months ago. My first client came through my network, and the next ones came from posting LinkedIn videos about what I was building. But I wanted something that scales without waiting for inbound. So I built a cold email automation pipeline from scratch. It handles the full flow: - Lead discovery using web scraping (Firecrawl + Google Maps data) - Email verification before any email goes out - AI-powered research per lead: website scrape, competitor analysis, needs analysis - Personalized 3-email sequences generated by AI with A/B testing on - subject lines, approaches and styles - Automated follow-up timing (day 1, day 3, day 7) - Reply detection via IMAP with AI classification into 6 categories - Human approval dashboard so nothing sends without review - Lead recycling for non-responders after 60 days The key insight: cold email is not about volume. It is about deep research per lead so the AI has enough context to write emails that actually feel personal. Every lead goes through a 7-step research process before a single word gets written. I put together a complete guide of 26 pages (PDF attached) that covers the full architecture, the actual AI prompts I use, SMTP setup, warmup strategy, deliverability tips, and the 10 mistakes I made building this. Hope it helps someone here!

.