4 papers
Compound AI System Reliability: A Failure Taxonomy and Resilience Pattern Catalog from 150 Production Incidents
Rudrendu Kumar Paul, Sourav Nandy
Deploying compound AI systems reliably and safely requires understanding failure modes that emerge at component boundaries, not within individual models. Cascading errors propagate…
AgentRouter: Heterogeneous Model Routing for Cost-Optimal Multi-Step Agentic Workflows
Rudrendu Kumar Paul, Sourav Nandy
Enterprise agentic systems that route every trajectory step to a frontier model waste 60-80% of their inference budget on subtasks that smaller models handle equally well. Existing…
Beyond Single-Model Injection: A Threat Model and Defense Architecture for Prompt Injection in Multi-Agent Systems
Rudrendu Kumar Paul, Sourav Nandy
Existing prompt injection research focuses on single-model chatbot scenarios, where an attacker manipulates one LLM through crafted input. Multi-agent systems amplify this threat t…
Governance-as-Code: Translating EU AI Act Technical Requirements into Executable Compliance Pipelines for Generative AI Systems
Rudrendu Kumar Paul, Sourav Nandy
The EU AI Act (Regulation 2024/1689) imposes technical obligations on high-risk AI providers, yet Articles 8-15 were drafted for predictive AI and leave seven technical gaps when a…