Case study · 02
AI-Powered Lead Enrichment, Scoring and Journey Routing
Enriches new leads, applies explainable AI-assisted scoring and routes each lead to sales, nurture or review through visible business rules.
System overview — a simplified portfolio diagram showing the governed path and human-control boundary.
Project overview
A clearer route from problem to action.
I designed an automated qualification and routing system that enriches company data, assesses fit and intent, calculates a transparent priority score and records the evidence and selected route in Airtable.
Business challenge
The friction behind the workflow
New enquiries often arrive with incomplete information, leaving teams to research companies and prioritise follow-up manually. Valuable leads may wait, while inconsistent decisions and unclear consent can create risk.
How it works
From input to controlled outcome
- 01
Validate and standardise the submitted lead data.
- 02
Enrich relevant company information with retry handling.
- 03
Give the model only the evidence needed for structured component scoring.
- 04
Validate the response and calculate the final score in visible workflow logic.
- 05
Route to sales, consent-controlled nurture, future review or manual review.
Designed value
What the system is built to improve
- Faster visibility of promising enquiries
- More consistent prioritisation
- Less repetitive company research
- A clear record of every automated decision
Responsible AI & human control
Automation supports judgement. It does not replace it.
- Sensitive characteristics are excluded
- Consent is checked before Braze nurture
- Uncertain or invalid responses go to manual review
- Duplicate alerts and actions are suppressed
- Audit records are written before activation
My contribution
Architecture, logic and safeguards
I defined the use case, architecture, scoring framework, consent and routing rules, Airtable model, duplicate prevention, error handling and credential separation.
Current validation status
Portfolio template with safe mock mode. The JSON structure is verified; live integrations and end-to-end production execution have not yet been evidenced.