9 papers
From ambiguous utterances to governed reuse classes: canonicalization, quotient invariance, and conditional decidability
Cosimo Spera, Ray Garcia
Semantic caching defines answer reuse on embedding similarity: two utterances share a stored answer when a similarity score clears a threshold, with no notion of authorization, ver…
Safety as Computation: Certified Answer Reuse via Capability Closure in Task-Oriented Dialogue
Cosimo Spera
We introduce a new paradigm for task-oriented dialogue systems: safety certification as a computational primitive for answer reuse. Current systems treat each turn independently, r…
Capability Safety as Datalog: A Foundational Equivalence
Cosimo Spera
We prove that capability safety admits an exact representation as propositional Datalog evaluation (Datalogprop: the monadic, ground, function-free fragment of first-order logic),…
From Workflow Automation to Capability Closure: A Formal Framework for Safe and Revenue-Aware Customer Service AI
Cosimo Spera
Customer service automation is undergoing a structural transformation. The dominant paradigm is shifting from scripted chatbots and single-agent responders toward networks of speci…
Safety is Non-Compositional: A Formal Framework for Capability-Based AI Systems
Cosimo Spera
This paper contains the first formal proof that safety is non-compositional in the presence of conjunctive capability dependencies: two agents each individually inca- pable of reac…
Redefining CX with Agentic AI: Minerva CQ Case Study
Garima Agrawal, Riccardo De Maria, Kiran Davuluri +5
Despite advances in AI for contact centers, customer experience (CX) continues to suffer from high average handling time (AHT), low first-call resolution, and poor customer satisfa…
Reversing the Paradigm: Building AI-First Systems with Human Guidance
Cosimo Spera, Garima Agrawal
The relationship between humans and artificial intelligence is no longer science fiction -- it's a growing reality reshaping how we live and work. AI has moved beyond research labs…
Beyond-RAG: Question Identification and Answer Generation in Real-Time Conversations
Garima Agrawal, Sashank Gummuluri, Cosimo Spera
In customer contact centers, human agents often struggle with long average handling times (AHT) due to the need to manually interpret queries and retrieve relevant knowledge base (…
Uniphore's submission to Fearless Steps Challenge Phase-2
Karthik Pandia D S, Cosimo Spera
We propose supervised systems for speech activity detection (SAD) and speaker identification (SID) tasks in Fearless Steps Challenge Phase-2. The proposed systems for both the task…