MODaaS, token economics & agentic AI - Building scalable AI-native operations

Sessions in rooms

Chair: Patrick Kelly, Founder & Principal Analyst, Appledore Research Group

Unified context for trusted data, AI, and agents

• Unified context is essential: Ground your organization in shared enterprise context across business units 
• Curate, don’t copy: The Zero-Copy principle keeps data at the source while making the right context available to agents in real-time
• Trusted data, better outcomes: Shared, authoritative governance enables more reliable and trustworthy AI

Nevash Pillay, Head of Global Telecom Industry, Databricks
Idilio Moncivais, Head of Financial Intelligence and Data Architecture, Lumen 
 
Make AI stick: The 4 moves to run an AI‑first telco 

• How to move AI out of pilots and into live operations across your business 
• How to redesign workflows and systems so AI drives operational decisions — not just reporting 
• How to make your organisation truly data‑driven, with the right foundations for AI at scale 
• Understand what the most successful adopters are doing differently — and how to apply it 

Christian Livia, CTO, Interbank

Taming AI spend: Token economics learnings from the frontline 

• From tokens to ROI: How telecoms operators are turning token consumption into measurable business value 
• Cutting cost without cutting capability: Practical lessons from model selection, routing and prompt optimisation to reduce inference spend at scale 
• Building AI cost discipline: What finance, technology and network teams need to know to forecast, govern and optimise rapidly growing AI workloads. 

Mark Austin, Vice President, Data Science, AT&T 

Bounded autonomy: Runtime governance for agentic AI in the enterprise

• Know when to intervene: Set clear runtime guardrails for autonomous AI agents
• Measure what matters: Track agent cost, token usage, risk, and business impact
• Scale with confidence: Build agentic AI that remains secure, accountable, and trustworthy.

Amarender Singh Sardar, Director of AI, EchoStar