Graph-Native Infrastructure for Context and Accountable AI Systems
Python agent-memoryaiai-governanceai-infrastructureartificial-intelligencecontext-engineeringcontext-graphsdata-engineeringdecision-intelligencedeveloper-toolsexplainable-aigenerative-aigraph-ragknowledge-graphllmontologyprovenancepythonreasoningsemantic-search
docs: make check_decision_rules examples pass the default policy (#1258) (#2004)
Zohaib Hassnain0bd39ccf7f99
diff --git a/README.md b/README.mdindex 410d077a..2967124f 100644--- a/README.md+++ b/README.md@@ -145,7 +145,15 @@ decision_id = graph.record_decision(chain = graph.trace_decision_chain(decision_id) # full causal ancestrysimilar = graph.find_similar_decisions("cloud vendor", max_results=5) # precedentsimpact = graph.analyze_decision_impact(decision_id) # downstream influence map-compliant = graph.check_decision_rules({"category": "vendor_selection"}) # policy gate++# Policy gate: checks the fields you pass against the default rules+# (confidence >= 0.7, outcome in approved/rejected/flagged, decision_maker set)+compliant = graph.check_decision_rules({+ "category": "vendor_selection",+ "outcome": "approved",+ "confidence": 0.93,+ "decision_maker": "platform-team",+}) # {'compliant': True, 'violations': [], ...}```**Verify your install in 5 seconds:**@@ -242,7 +250,12 @@ graph.add_causal_relationship(uw_id, rate_id, relationship_type="INFLUENCED")chain = graph.trace_decision_chain(rate_id)similar = graph.find_similar_decisions("personal loan approval, 31% DTI", max_results=5)impact = graph.analyze_decision_impact(uw_id)-compliant = graph.check_decision_rules({"category": "loan_underwriting", "confidence": 0.94})+compliant = graph.check_decision_rules({+ "category": "loan_underwriting",+ "outcome": "approved",+ "confidence": 0.94,+ "decision_maker": "underwriting_agent",+})insights = graph.get_decision_insights()```diff --git a/semantica/context/context_usage.md b/semantica/context/context_usage.mdindex 434d22db..1f4257d9 100644--- a/semantica/context/context_usage.md+++ b/semantica/context/context_usage.md@@ -211,7 +211,8 @@ compliance = knowledge.check_decision_rules({"scenario": "Mortgage application","reasoning": "Good credit score, stable income","outcome": "approved",- "confidence": 0.95+ "confidence": 0.95,+ "decision_maker": "loan_officer"})if compliance.get("compliant", False):