Hi everyone, I’m looking for someone with strong n8n + OpenAI/AI Agent expertise who can help me upgrade an existing WhatsApp-based workflow into a more natural, conversational experience. I’ve already built the core workflow using n8n, WhatsApp and Airtable, with separate workflows for airport transfers, railway routes, intercity travel and full-day rentals. I’m looking to introduce an AI conversational layer without rebuilding the existing system. I’ll share a screenshot of the current workflow to give you a clear idea of the scope and complexity. If you have relevant experience and can help architect and implement this, please DM me. Open to discussing your fees based on the scope of work. Allan

Hello everyone — I recently shared that I’m branching out to help businesses with automation, and a warm lead reached out. They’re a fairly large ecommerce company advertising across roughly seven platforms. Their CMO wants a centralized internal hub that could: - Pull performance data from multiple ad platforms into one dashboard - Surface winning creatives based on defined rules - Identify possible opportunities to test winning concepts across platforms - Show creative-pipeline status from Trello - Eventually add AI-assisted analysis and recommendations It sounds like this may go beyond a typical automation project and into internal software/product territory. I have built advanced n8n automations for the company I currently work with, and I’ve built smaller desktop applications with AI coding tools. I’m comfortable with automation, databases, and integrations, so I did come with a strong recommendation from this other company which helps. But I do want to be realistic about the scope and not promise a custom platform I can’t reliably maintain. My initial thought is to scope it in phases: 1. Validate API access and reporting availability for the priority platforms. I know some can require special applications for access. 2. Sync the two most important sources—likely Meta and Google Ads—into Postgres daily. 3. Build a useful first reporting dashboard from that data. 4. Add remaining priority ad platforms in later phases. 5. Add rule-based flags and Slack/email/dashboard notifications based on the CMO’s thresholds. 6. Add Trello pipeline visibility. 7. Add AI-assisted summaries and recommendations grounded in the approved data and rules, with human review. I would keep the initial phases read-only: no automated campaign changes or autonomous decisions. My biggest questions are: - Have you built something similar solo? What were the biggest technical or maintenance pitfalls? - How would you scope and price the initial data/dashboard phase being that I don’t have specific experience with something like this? - At what point would you say this needs a dedicated software engineer rather than an automation builder?

How do you know your client automations are actually working? Genuine question for people running automations for clients. Individual tools tell you when they break. n8n emails you on workflow failure, Make has error handling, etc. But that only covers failures inside that one tool. What I keep running into is the other kind: every tool reports success, no error fires anywhere, and the outcome still didn't happen. Lead doesn't reach the CRM. Record arrives but half the fields are empty. Everything green, client quietly losing money. How are you catching these? Manually checking? Building your own reconciliation? Just waiting for the client to complain? And separately, how do you prove to a client that their system IS working in the months when nothing goes wrong? I've never had a good answer for that one.

Which N8N nodes do beginners usually miss or not realize should be used? I'm looking for the nodes that experienced builders reach for all the time, but beginners either don't know exist or don't realize when to use them. The ones where a pro would look at a beginner's workflow and say "you should've used this node here instead." What are those must-know nodes in real-world workflows?

I'm the AI consultant for an Australian mortgage brokerage (Sydney, small team). I want an internal assistant every employee can ask about how the company works — our processes/SOPs, which lenders suit which client scenarios, fees, compliance rules, who does what. Where I've got to so far: - Anchor use case: internal SOP/process assistant. Not client-facing. - Access: private login-gated web chat portal — staff sign in with their company email, public can't get in. - Guardrail: it must cite its source and say "I don't have that documented — ask X" rather than guess. We're regulated; a confident wrong answer about lender policy is worse than no answer. - The discovery that changed everything: I audited our Google Drive expecting SOPs. There were almost none — it's all marketing material. The real process knowledge is in the director's head. The bottleneck is content, not tech. - My plan: one curated company knowledge-base doc as the agent's brain (small enough to fit in the model's context, so no vector DB), an admin screen to edit it, and logging every question the agent can't answer — that log becomes the prioritised list of what to document next, so it bootstraps itself. What I'd love input on: 1. Is "whole KB in the system prompt, skip RAG" sane for a small company KB? At what size does that break and force vector search? 2. How did you get knowledge out of people's heads? This is my real blocker. Interviews? Recording client calls and mining them? What actually worked? 3. Anyone shipped this with no-code (Custom GPT / Claude Project / n8n) vs. a custom app? Where's the line where custom becomes worth it? 4. For a small team, is a login-gated custom app overkill vs. just sharing a Claude Project with team seats? 5. War stories: what killed adoption of an internal agent? What made staff actually trust it? Stack: Next.js + Supabase + Vercel, Claude API. Happy to share back what I learn.