Sales and client calls generated commitments, risks and next steps that lived only in someone's memory or scattered notes — nothing was tracked systematically, so deals stalled and action items slipped through unnoticed.
We built a 3-agent n8n pipeline that ingests a meeting transcript, audio, video or Drive file and runs it through a chain of specialist AI agents: one extracts metadata, participants and action items; a second analyses sentiment, objections, risk and CRM deal-stage progression; a third synthesises everything into a client email, internal digest and calendar-ready summary — plus a daily digest of all open action items across every meeting.
What we did
Here's how we approached A B2B SaaS company's project, step by step.
Accepts transcript text, audio, video or Drive files — auto-transcribes non-text input
Agent 1: extracts meeting metadata, participants, decisions and action items with owners and deadlines
Agent 2: sentiment scoring, objection and competitor detection, risk flagging, CRM deal-stage advice
Agent 3: synthesises findings into an email, internal digest and calendar summary
Daily 8AM digest of all open action items across every meeting
Results & impact
- Every client call converted into structured, trackable intelligence automatically
- No more missed commitments or forgotten follow-ups
- Objective, transcript-based deal-health and risk scoring for every sales call
- Reusable pattern — works for sales calls, client check-ins or internal meetings alike
Want something like this for your business?
We build websites, ecommerce stores and AI automation for businesses worldwide — and we'll tell you honestly what you actually need. Book a free 30-minute call and we'll map out your project, costs and timeline.
Book a Free Call