proposal-draft threshold
Case study 02 · AI workflow design · Revenue operations
Meridian Systems
Practical AI systems that turn document intake and prospecting into structured, reviewable operating workflows.
Role
Founder · Managing Director · CTO
Status
Internal tools and product demonstrations
AI handles the repetitive work while people stay in control of the important decisions.
01The challenge
Start with the
business problem.
Teams lose expensive hours moving information between inboxes, documents and CRMs. The opportunity is not simply to add AI, but to design a dependable decision path around it.
02The approach
How I
approached it.
- 01
Created a synthetic KYC demonstration that extracts structured document fields and branches cleanly into approval or re-upload.
- 02
Built a lead engine that monitors opportunities, scores fit and drafts proposals above a controlled threshold.
- 03
Kept human review at the point of consequence while automating collection, classification and hand-off.
03System architecture
How the parts
work together.
01
Document upload
→02
Gemini extraction
→03
Validation branch
→04
CRM hand-off
→05
Opportunity monitoring
→06
Human review
04Evidence
Results and evidence.
deterministic KYC outcomes
intake through CRM hand-off
Figures distinguish reported business outcomes from repository-evidenced architecture. Prototype and staged capabilities are labelled to avoid overstating production status.
Selected technology
ReactTypeScriptGeminin8nSupabaseExpressOdoo
Continue the conversation