Shared inbox automation

AI inbox copilot for a small accountancy firm

Monitors a shared Outlook inbox, classifies every incoming client email, decides if a reply or follow-up action is needed, and drafts or sends responses grounded in the firm's knowledge. The team went from manually triaging >50 client emails a day to reviewing high-quality drafts, one-click approvals and focusing on edge cases.

Emails triaged / month
1,500-2,400
Time saved / month
~50h
Replies auto-drafted
≈70%
LLM calls avoided
-40% vs naive
Classification
Priority routing
Responder
Knowledge Base
Multilingual
Metrics & Tracking
No Training
Outbound lead generation

Multi-vertical podcast booking engine

Engineered a multi-niche outreach system that identifies qualified podcasts across four distinct verticals (AI systems, spiritual coaching, business & entrepreneurship, and mompreneur), crafts host-specific pitches referencing recent episodes and guests, classifies every reply with AI, and drafts on-brand responses using lane-aware voice selection. Across 2,400 outreach emails the campaign delivered a 15% reply rate (3x industry average) with over half of all replies expressing genuine interest in booking.

Reply rate
15%
Positive reply rate
55.56%
Pipeline generated
$600k-$1M
vs. industry avg
3× higher
Multi-niche outreach
Reply classification
Lane-aware AI drafting
CRM pipeline
Booking detection
4 audience verticals