Most internal chatbots have the same flaw: ask about a policy and they confidently invent an answer they don't actually have. Useless for ops, and worse than useless if someone acts on it.
This reference build fixes that by construction. Staff ask a question in Microsoft Teams, one router agent reads it and hands it to the right role-scoped specialist, and each specialist answers only from its own SOP knowledge base. No source, no answer. The pattern is configurable to whatever role split an organization runs on.
Built on n8n with per-domain retrieval, and documented from the build so an ops team can run and extend it without me. Reference build on synthetic SOPs. Full architecture and write-up in the case study.
What if every new lead could be handled before you even open your inbox? ⚡
This AI-powered workflow turns a new email inquiry into a structured, ready-to-handle lead — automatically.
A new inquiry arrives → AI extracts the important details → Airtable/CRM is updated → the response goes through optional human approval → a personalized email is sent → Notion is updated → the team gets notified in Slack → performance data is collected for reporting.
The goal isn't to remove people from the process. It's to remove the repetitive work around them.
This type of workflow can be customized for B2B companies, SaaS businesses, agencies, real estate, e-commerce, recruitment, consulting, customer support, healthcare, finance, education, and other service businesses.
Already know what you want to automate? → Send me your current workflow and I’ll map out how we can automate it.
Still doing repetitive work manually? → Tell me the task that consumes your team’s time, and I’ll help identify what can be automated.
I'd use the human approval step to capture corrections, not just a yes/no decision. If a reviewer changes the extracted lead details, does the workflow update Airtable and the reporting record before sending the email?
Built an n8n CRM automation system that captures leads, creates and updates CRM records, assigns tasks, sends team notifications, automates follow-ups and generates reports.
I built an AI voice ordering workflow to help a restaurant capture customer orders and pass them to the kitchen with less manual work.
Using Vapi, I configured a voice assistant with the restaurant’s menu and prices to collect customer details and orders. After each call, a webhook triggers an n8n workflow, where OpenAI extracts the order into structured data. The workflow then notifies the kitchen and logs the order in Google Sheets.
I handled the voice assistant setup, webhook integration, AI prompts, and workflow implementation. The solution reduced manual order entry and made order information easier for the kitchen to access.
Tools: Vapi, n8n, OpenAI, Google Sheets, and webhooks.