Create lead_scoring_agent.py

lead_scoring_agent.py

@@ -0,0 +1,73 @@
+"""
+lead_scoring_agent.py
+---
+ML/transformer+rule agent that ingests full lead/profile asset and outputs:
+  - intent_score: Float
+  - readiness: Category (e.g., 'ready', 'researching', 'cold')
+  - segment: Category (e.g., 'SMB', 'Enterprise', 'Freelancer')
+  - rationale/feature_importance: Dict[str, float] (reasons/score contributions)
+
+Integrates with enrichment, research, outreach, analytics, validation agents. See README for pipeline, hooks, and agent call documentation.
+"""
+
+from transformers import pipeline
+import numpy as np
+
+class LeadScoringAgent:
+    def __init__(self, model_name: str = 'distilbert-base-uncased'):
+        self.classifier = pipeline('text-classification', model=model_name)
+
+    def score_lead(self, profile: dict) -> dict:
+        text = self.profile_to_text(profile)
+        model_result = self.classifier(text)[0]
+        intent_score = float(model_result['score'])
+        label = model_result['label'].lower()
+
+        # Rule-based logic (customize as needed)
+        readiness = 'ready' if intent_score > 0.8 and 'purchase' in label else 'researching' if intent_score > 0.5 else 'cold'
+        segment = self.segment_from_profile(profile)
+        feature_importance = self.estimate_feature_importance(profile)
+        rationale = {k: v for k, v in feature_importance.items() if abs(v) > 0.1}
+
+        return {
+            'intent_score': intent_score,
+            'readiness': readiness,
+            'segment': segment,
+            'rationale': rationale,
+            'feature_importance': feature_importance
+        }
+
+    def profile_to_text(self, profile: dict) -> str:
+        # Join relevant fields into text
+        fields = ['bio', 'recent_activity', 'interests', 'company', 'role']
+        return ' '.join([str(profile.get(f, '')) for f in fields])
+
+    def segment_from_profile(self, profile: dict) -> str:
+        size = profile.get('company_size', '').lower()
+        if 'enterprise' in size or profile.get('employees', 0) > 1000:
+            return 'Enterprise'
+        elif 'small' in size or profile.get('employees', 0) < 50:
+            return 'SMB'
+        return 'Freelancer' if 'freelancer' in profile.get('role', '').lower() else 'SMB'
+
+    def estimate_feature_importance(self, profile: dict) -> dict:
+        imp = {}
+        imp['bio_len'] = len(profile.get('bio', '')) / 100.0
+        imp['activity'] = len(profile.get('recent_activity', '')) / 50.0
+        imp['interest_match'] = 1.0 if 'AI' in profile.get('interests', '') else 0.0
+        imp['company_rep'] = 1.0 if 'Google' in profile.get('company', '') else 0.2
+        return imp
+
+# Example usage:
+if __name__ == '__main__':
+    agent = LeadScoringAgent()
+    profile = {
+        'bio': 'Experienced AI practitioner looking to purchase cloud solutions.',
+        'recent_activity': 'Demo requested.',
+        'interests': 'AI, Machine Learning, Cloud',
+        'company': 'Google',
+        'role': 'Manager',
+        'company_size': 'enterprise',
+        'employees': 1200
+    }
+    print(agent.score_lead(profile))